Awesome Source-Free Domain Adaptation

A curated list of awesome source-free domain adaptation resources. Your contributions are always welcome!

Shallow Methods

MCFA/ACM/TPA [Chidlovskii and Orabona, Proc. KDD 2016] Domain adaptation in the absence of source domain data [PDF] [G-Scholar]
TPAe [Clinchant et al., Proc. ACL 2016] Transductive adaptation of black box predictions [PDF] [G-Scholar]
RWA [Van Laarhoven and Marchiori, arXiv 2017] Unsupervised domain adaptation with random walks on target labelings [PDF] [G-Scholar] [CODE]
AOT [Nelakurthi et al., Proc. IEEE BigData 2018] Source free domain adaptation using an off-the-shelf classifier [PDF] [G-Scholar]
MCS [Liang et al., Proc. CVPR 2019] Distant supervised centroid shift: A simple and efficient approach to visual domain adaptation [PDF] [G-Scholar] [CODE]

Image Classification

2020

SHOT [Liang et al., Proc. ICML 2020] Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
3C-GAN [Li et al., Proc. CVPR 2020] Model adaptation: Unsupervised domain adaptation without source data [PDF] [G-Scholar]
Inheritune [Kundu et al., Proc. CVPR 2020] Towards inheritable models for open-set domain adaptation [PDF] [G-Scholar] [CODE]
USFDA [Kundu et al., Proc. CVPR 2020] Universal source-free domain adaptation [PDF] [G-Scholar] [CODE]
PLR [Morerio et al., Proc. WACV 2020] Generative pseudo-label refinement for unsupervised domain adaptation [PDF] [G-Scholar]
SFDA-TN [Sahoo et al., Proc. ICML Workshops 2020] Unsupervised domain adaptation in the absence of source data [PDF] [G-Scholar]
PPDA [Kim et al., IEEE SPL 2020] Towards privacy-preserving domain adaptation [PDF] [G-Scholar]
SFDA-IT [Hou and Zheng, arXiv 2020] Source free domain adaptation with image translation [PDF] [G-Scholar]
UMSDE [Zhang et al., arXiv 2020] Unsupervised domain expansion from multiple sources [PDF] [G-Scholar]
TAN [ Xu and Kang, Misc 2020] Transfer alignment network for double blind unsupervised domain adaptation [PDF] [G-Scholar]

2021

HCL [Huang et al., Proc. NeurIPS 2021] Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data [PDF] [G-Scholar] [CODE]
PCT [Tanwisuth et al., Proc. NeurIPS 2021] A prototype-oriented framework for unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
CAiDA [Dong et al., Proc. NeurIPS 2021] Confident anchor-induced multi-source free domain adaptation [PDF] [G-Scholar] [CODE]
LDAuCID [Rostami, Proc. NeurIPS 2021] Lifelong domain adaptation via consolidated internal distribution [PDF] [G-Scholar] [CODE]
NRC [Yang et al., Proc. NeurIPS 2021] Exploiting the intrinsic neighborhood structure for source-free domain adaptation [PDF] [G-Scholar] [CODE]
TTT++ [Liu et al., Proc. NeurIPS 2021] TTT++: When does self-supervised test-time training fail or thrive? [PDF] [G-Scholar] [CODE]
SFIT [Hou and Zheng, Proc. CVPR 2021] Visualizing adapted knowledge in domain transfer [PDF] [G-Scholar] [CODE]
A2Net [Xia et al., Proc. CVPR 2021] Adaptive adversarial network for source-free domain adaptation [PDF] [G-Scholar]
DECISION [Ahmed et al., Proc. CVPR 2021] Unsupervised multi-source domain adaptation without access to source data [PDF] [G-Scholar] [CODE]
G-SFDA [Yang et al., Proc. ICCV 2021] Generalized source-free domain adaptation [PDF] [G-Scholar] [CODE]
HDMI [Lao et al., Proc. AAAI 2021] Hypothesis disparity regularized mutual information maximization [PDF] [G-Scholar]
CPGA [Qiu et al., Proc. IJCAI 2021] Source-free domain adaptation via avatar prototype generation and adaptation [PDF] [G-Scholar] [CODE]
ISFDA [Li et al., Proc. ACMMM 2021] Imbalanced source-free domain adaptation [PDF] [G-Scholar] [CODE]
IterLNL [Zhang et al., Proc. BMVC 2021] Unsupervised domain adaptation of black-box source models [PDF] [G-Scholar] [CODE]
SSFT-SSD [Yan et al., Proc. BMVC 2021] Source-free unsupervised domain adaptation with surrogate data generation [PDF] [G-Scholar]
SDDA [Kurmi et al., Proc. WACV 2021] Domain impression: A source data free domain adaptation method [PDF] [G-Scholar] [CODE]
SoFA [Yeh et al., Proc. WACV 2021] SoFA: Source-data-free feature alignment for unsupervised domain adaptation [PDF] [G-Scholar]
GKD [Tang et al., Proc. IROS 2021] Model adaptation through hypothesis transfer with gradual knowledge distillation [PDF] [G-Scholar] [CODE]
ASL [Yan et al., Proc. NeurIPS Workshops 2021] Augmented self-labeling for source-free unsupervised domain adaptation [PDF] [G-Scholar]
ADV-M [Wang et al., Proc. ICETIS 2021] Providing domain specific model via universal no data exchange domain adaptation [PDF] [G-Scholar]
DECDA [Zhu, Proc. DSIT 2021] Source free domain adaptation by deep embedding clustering [PDF] [G-Scholar]
SHOT++ [Liang et al., IEEE TPAMI 2021] Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer [PDF] [G-Scholar] [CODE]
DI [Nayak et al., IEEE TPAMI 2021] Mining data impressions from deep models as substitute for the unavailable training data [PDF] [G-Scholar]
LA-VAE [Yang et al., IEEE TIP 2021] Model-induced generalization error bound for information-theoretic representation learning in source-data-free unsupervised domain adaptation [PDF] [G-Scholar]
OSHT-SC [Feng et al., IEEE TIP 2021] Open-set hypothesis transfer with semantic consistency [PDF] [G-Scholar]
VDM-DA [Tian et al., IEEE TCSVT 2021] VDM-DA: Virtual domain modeling for source data-free domain adaptation [PDF] [G-Scholar]
SFDA-APM [Kim et al., IEEE TAI 2021] Domain adaptation without source data [PDF] [G-Scholar]
PIDM [Ma et al., Knowledge-Based Systems 2022] Source-free semi-supervised domain adaptation via progressive Mixup [PDF] [G-Scholar]

~~[Ma et al., arXiv 2021] Uncertainty-guided mixup for semi-supervised domain adaptation without source data [PDF]~~
TransDA [Yang et al., Applied Intelligence 2022] Self-training transformer for source-free domain adaptation [PDF] [G-Scholar] [CODE]

~~[Yang et al., arXiv 2021] Transformer-based source-free domain adaptation [PDF]~~
STDA [Tian et al., Journal of Computer Science and Technology 2021] Source-free unsupervised domain adaptation with sample transport learning [PDF] [G-Scholar]
OnTA [Wang et al., arXiv 2021] On-target adaptation [PDF] [G-Scholar]
SFDA-MBNS [Ishii and Sugiyama, arXiv 2021] Source-free domain adaptation via distributional alignment by matching batch normalization statistics [PDF] [G-Scholar]
N2DC-EX [Tang et al., arXiv 2021] Nearest neighborhood-based deep clustering for source data-absent unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
BAIT [Yang et al., arXiv 2021] Casting a BAIT for offline and online source-free domain adaptation [PDF] [G-Scholar] [CODE]
UMAD [Liang et al., arXiv 2021] UMAD: Universal model adaptation under domain and category shift [PDF] [G-Scholar]
SMUDA [Stan and Rostami, arXiv 2021] Secure domain adaptation with multiple sources [PDF] [G-Scholar]
UB2DA-ST [Deng et al., arXiv 2021] On universal black-box domain adaptation [PDF] [G-Scholar] [CODE]
USFDA-DAT [Wu et al., arXiv 2021] Domain adaptation without model transferring [PDF] [G-Scholar]
CDL [Wang et al., arXiv 2021] Learning invariant representation with consistency and diversity for semi-supervised source hypothesis transfer [PDF] [G-Scholar] [CODE]

2022

CoWA-JMDS [Lee et al., Proc. ICML 2022] Confidence score for source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
SFDA-mixup [Kundu et al., Proc. ICML 2022] Balancing discriminability and transferability for source-free domain adaptation [PDF] [G-Scholar]
AaD [Yang et al., Proc. NeurIPS 2022] Attracting and dispersing: A simple approach for source-free domain adaptation [PDF] [G-Scholar] [CODE]
VMP [Jing et al., Proc. NeurIPS 2022] Variational model perturbation for source-free domain adaptation [PDF] [G-Scholar] [CODE]
DaC [Zhang et al., Proc. NeurIPS 2022] Divide and contrast: Source-free domain adaptation via adaptive contrastive learning [PDF] [G-Scholar] [CODE]
BUFR [Eastwood et al., Proc. ICLR 2022] Source-free adaptation to measurement shift via bottom-up feature restoration [PDF] [G-Scholar] [CODE]
DINE [Liang et al., Proc. CVPR 2022] DINE: Domain adaptation from single and multiple black-box predictors [PDF] [G-Scholar] [CODE]
SFDA-DE [Ding et al., Proc. CVPR 2022] Source-free domain adaptation via distribution estimation [PDF] [G-Scholar] [CODE]
AdaContrast [Chen et al., Proc. CVPR 2022] Contrastive test-time adaptation [PDF] [G-Scholar] [CODE]
DIPE [Wang et al., Proc. CVPR 2022] Exploring domain-invariant parameters for source free domain adaptation [PDF] [G-Scholar]
BMD [Qu et al., Proc. ECCV 2022] BMD: A general class-balanced multicentric dynamic prototype strategy for source-free domain adaptation [PDF] [G-Scholar] [CODE]
U-SFAN [Roy et al., Proc. ECCV 2022] Uncertainty-guided source-free domain adaptation [PDF] [G-Scholar] [CODE]
KUDA [Sun et al., Proc. ECCV 2022] Prior knowledge guided unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
StickerDA [Kundu et al., Proc. ECCV 2022] Concurrent subsidiary supervision for unsupervised source-free domain adaptation [PDF] [G-Scholar] [CODE]
D-MCD [Chu et al., Proc. AAAI 2022] Denoised maximum classifier discrepancy for source-free unsupervised domain adaptation [PDF] [G-Scholar]
ELPT [Li et al., Proc. ACMMM 2022] Source-free active domain adaptation via energy-based locality preserving transfer [PDF] [G-Scholar]
PCSR [Guan et al., Proc. BMVC 2022] Polycentric clustering and structural regularization for source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
DMAPL [Yan and Guo, Proc. BMVC 2022] Dual moving average pseudo-labeling for source-free inductive domain adaptation [PDF] [G-Scholar] [CODE]
R-SFDA [Agarwal et al., Proc. WACV 2022] Unsupervised robust domain adaptation without source data [PDF] [G-Scholar]
NEL [Ahmed et al., Proc. WACV 2022] Cleaning noisy labels by negative ensemble learning for source-free unsupervised domain adaptation [PDF] [G-Scholar]

~~[Ahmed et al., arXiv 2021] Adaptive pseudo-label refinement by negative ensemble learning for source-free unsupervised domain adaptation [PDF]~~
VDB [Yazdanpanah and Moradi, Proc. CVPR Workshops 2022] Visual domain bridge: A source-free domain adaptation for cross-domain few-shot learning [PDF] [G-Scholar] [CODE]
PDA-MCD [Bohdal et al., Proc. ECCV Workshops 2022] Feed-forward source-free domain adaptation via class prototypes [PDF] [G-Scholar]
SSNLL [Chen et al., Proc. IROS 2022] Self-supervised noisy label learning for source-free unsupervised domain adaptation [PDF] [G-Scholar]
GAM [Li et al., Proc. IJCNN 2022] Source-free multi-domain adaptation with generally auxiliary model training [PDF] [G-Scholar]
CSFA [Yeh et al., Proc. ICPR 2022] Boosting source-free domain adaptation via confidence-based subsets feature alignment [PDF] [G-Scholar]
SFISA [Zhang and Zhang, Proc. PRICAI 2022] Source-free implicit semantic augmentation for domain adaptation [PDF] [G-Scholar]
c-FeaGen [Xu et al., Proc. IGARSS 2022] Source-free domain adaptation for cross-scene hyperspectral image classification [PDF] [G-Scholar]
DC-WSL [Song et al., Proc. ICNSC 2022] SS8: Source data-free domain adaptation via deep clustering with weighted self-labelling [PDF] [G-Scholar]
SFDA-DML [Zhang and Tian, Proc. ICCWAMTIP 2022] Source-free unsupervised domain adaptation via denoising mutual learning [PDF] [G-Scholar]
DEB [Sun et al., Proc. DSIT 2022] Source-free unsupervised domain adaptation in imbalanced datasets [PDF] [G-Scholar] [CODE]
SCLM [Tang et al., Neural Networks 2022] Semantic consistency learning on manifold for source data-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
DEEM [Ma et al., Neural Networks 2022] Context-guided entropy minimization for semi-supervised domain adaptation [PDF] [G-Scholar] [CODE]
CDCL [Wang et al., IEEE TMM 2022] Cross-domain contrastive learning for unsupervised domain adaptation [PDF] [G-Scholar]
SFUDA-TPS [Tian et al., ACM TIST 2022] Source-free unsupervised domain adaptation with trusted pseudo samples [PDF] [G-Scholar]
RPL [Rusak et al., TMLR 2022] If your data distribution shifts, use self-learning [PDF] [G-Scholar] [CODE]
SAB [Liu et al., IEEE SPL 2022] Self-alignment for black-box domain adaptation of image classification [PDF] [G-Scholar]
CdKD-TSML [Li et al., Knowledge-Based Systems 2022] Teacher-student mutual learning for efficient source-free unsupervised domain adaptation [PDF] [G-Scholar]
SFDA-ADT [Liu et al., Applied Intelligence 2022] A source free domain adaptation model based on adversarial learning for image classification [PDF] [G-Scholar]

~~[Liu et al., Proc. IJCNN 2022] Source free domain adaptation via combined discriminative GAN model for image classification [PDF]~~
Prototype-DA [Zhou et al., Neural Computing and Applications 2022] Domain adaptation based on source category prototypes [PDF] [G-Scholar]
SFMBD [Tian et al., Computers and Electrical Engineering 2022] Source-free unsupervised domain adaptation with maintaining model balance and diversity [PDF] [G-Scholar]
LCCL [Zhao et al., Sensors 2022] Adaptive contrastive learning with label consistency for source data free unsupervised domain adaptation [PDF] [G-Scholar]
JN [Li et al., arXiv 2022] Jacobian norm for unsupervised source-free domain adaptation [PDF] [G-Scholar]
DAMC [Zong et al., arXiv 2022] Domain gap estimation for source free unsupervised domain adaptation with many classifiers [PDF] [G-Scholar] [CODE]
RCHC [Diamant et al., arXiv 2022] Reconciling a centroid-hypothesis conflict in source-free domain adaptation [PDF] [G-Scholar] [CODE]
SF-PGL [Luo et al., arXiv 2022] Source-free progressive graph learning for open-set domain adaptation [PDF] [G-Scholar] [CODE]
UTR [Pei et al., arXiv 2022] Uncertainty-induced transferability representation for source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
EXTERN [Xu et al., arXiv 2022] EXTERN: Leveraging endo-temporal regularization for black-box video domain adaptation [PDF] [G-Scholar]
... [Al-Maliki et al., arXiv 2022] Continual conscious active fine-tuning to robustify online machine learning models against data distribution shifts [PDF] [G-Scholar]
OneRing [Yang et al., arXiv 2022] One ring to bring them all: Model adaptation under domain and category shift [PDF] [G-Scholar] [CODE]
DePT [Gao et al., Misc 2022] Visual prompt tuning for test-time domain adaptation [PDF] [G-Scholar]
FTA-FDA [Peng, Thesis 2022] Multi-source and source-private cross-domain learning for visual recognition [PDF] [G-Scholar]

2023

ELR [Yi et al., Proc. ICLR 2023] When source-free domain adaptation meets learning with noisy labels [PDF] [G-Scholar] [CODE]
BETA [Yang et al., Proc. ICLR 2023] Divide to adapt: Mitigating confirmation bias for domain adaptation of black-box predictors [PDF] [G-Scholar] [CODE]
Twofer [Liu et al., Proc. ICLR 2023] Twofer: Tackling continual domain shift with simultaneous domain generalization and adaptation [PDF] [G-Scholar]
SQRL [Naik et al., Proc. ICML 2023] Do machine learning models learn statistical rules inferred from data? [PDF] [G-Scholar] [CODE--]
... [Shen et al., Proc. ICML 2023] On balancing bias and variance in unsupervised multi-source-free domain adaptation [PDF] [G-Scholar]

~~[Shen et al., arXiv 2022] On the benefits of selectivity in pseudo-labeling for unsupervised multi-source-free domain adaptation [PDF] [G-Scholar]~~
SODA [Wang et al., Proc. NeurIPS 2023] SODA: Robust training of test-time data adaptors [PDF] [G-Scholar]
CODA [Chen et al., Proc. NeurIPS 2023] CODA: Generalizing to open and unseen domains with compaction and disambiguation [PDF] [G-Scholar] [CODE]
FedICON [Tan et al., Proc. NeurIPS 2023] Is heterogeneity notorious? Taming heterogeneity to handle test-time shift in federated learning [PDF] [G-Scholar]
MHPL [Wang et al., Proc. CVPR 2023] MHPL: Minimum happy points Learning for active source free domain adaptation [PDF] [G-Scholar]

~~[Wang et al., arXiv 2022] Active source free domain adaptation [PDF] [G-Scholar]~~
PLUE [Litrico et al., Proc. CVPR 2023] Guiding pseudo-labels with uncertainty estimation for source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]

~~[Litrico et al., arXiv 2023] Guiding pseudo-labels with uncertainty estimation for test-time adaptation [PDF] [G-Scholar] [CODE]~~
GLC [Qu et al., Proc. CVPR 2023] Upcycling models under domain and category shift [PDF] [G-Scholar] [CODE]
C-SFDA [Karim et al., Proc. CVPR 2023] C-SFDA: A curriculum learning aided self-training framework for efficient source free domain adaptation [PDF] [G-Scholar]
DiaNA [Huang et al., Proc. CVPR 2023] Divide and adapt: Active domain adaptation via customized learning [PDF] [G-Scholar]
CRCo [Huang et al., Proc. CVPR 2023] Class relationship embedded learning for source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
SSDA [Ahmed et al., Proc. ICCV 2023] SSDA: Secure source-free domain adaptation [PDF] [G-Scholar] [CODE]
BiMem [Zhang et al., Proc. ICCV 2023] Black-box unsupervised domain adaptation with bi-directional atkinson-shiffrin memory [PDF] [G-Scholar] [CODE]
DSiT [Sanyal et al., Proc. ICCV 2023] Domain-specificity inducing transformers for source-free domain adaptation [PDF] [G-Scholar] [CODE--]
... [Hu et al., Proc. ICCV 2023] DandelionNet: Domain composition with instance adaptive classification for domain generalization [PDF] [G-Scholar--]
Co-learn [Zhang et al., Proc. ICCV 2023] Rethinking the role of pre-trained networks in source-free domain adaptation [PDF] [G-Scholar--]

~~[Zhang et al., arXiv 2022] Co-learning with pre-trained networks improves source-free domain adaptation [PDF] [G-Scholar]~~
CoDAG [Cho et al., Proc. ICCV 2023] Complementary domain adaptation and generalization for unsupervised continual domain shift learning [PDF] [G-Scholar]
APA [Sun et al., Proc. AAAI 2023] Domain adaptation with adversarial training on penultimate activations [PDF] [G-Scholar] [CODE]
DATE [Han et al., Proc. AAAI 2023] Discriminability and transferability estimation: A bayesian source importance estimation approach for multi-source-free domain adaptation [PDF] [G-Scholar]
RAIN [Peng et al., IJCAI 2023] RAIN: Regularization on input and network for black-box domain adaptation [PDF] [G-Scholar] [CODE]
CtO [Wu et al., Proc. ACMMM 2023] Chaos to order: A label propagation perspective on source-free domain adaptation [PDF] [G-Scholar--]
CoDE [Shen et al., Proc. ACMMM 2023] Collaborative learning of diverse experts for source-free universal domain adaptation [PDF] [G-Scholar--]
CATTAn [Thopalli et al., Proc. ACCV 2023] Domain alignment meets fully test-time adaptation [[PDF]](https://proceedings.mlr.press/v189/thopalli23a.html [G-Scholar] [CODE]

~~[Thopalli et al., Proc. ECCV Workshops 2022] Geometric alignment improves fully test time adaptation [PDF] [G-Scholar]~~
CoNMix [Kumar et al., Proc. WACV 2023] Conmix for source-free single and multi-target domain adaptation [PDF] [G-Scholar] [CODE]
GAP [Chhabra et al., Proc. WACV 2023] Generative alignment of posterior probabilities for source-free domain adaptation [PDF] [G-Scholar]
SALAD [Kothandaraman et al., Proc. WACV 2023] SALAD: Source-free active label-agnostic domain adaptation for classification, segmentation and detection [PDF] [G-Scholar] [CODE]

~~[Kothandaraman et al., arXiv 2022] DistillAdapt: Source-free active visual domain adaptation [PDF]~~
NHOT [Cao et al., Proc. ICASSP 2023] Nasty-SFDA: Source free domain adaptation from a nasty model [PDF] [G-Scholar]
C-SUDA [Ahmed et al., Proc. ICIAP 2023] Continual source-free unsupervised domain adaptation [PDF] [G-Scholar]
CIN [Tang et al., Proc. ICIP 2023] Cross-inferential networks for source-free unsupervised domain adaptation [PDF] [G-Scholar]
RAT [Xiao et al., Proc. ICME 2023] Adversarially robust source-free domain adaptation with relaxed adversarial training [PDF] [G-Scholar] [CODE]
ISKD [Wang et al., Proc. ICME 2023] Information selection-based domain adaptation from black-box predictors [PDF] [G-Scholar]
TransMDA [Li and Wu, Proc. IJCNN 2023] Transformer-based multi-source domain adaptation without source data [PDF] [G-Scholar--]
SSG-SFDA [An et al., Proc. IJCNN 2023] Semi-supervised generalized source-free domain adaptation (SSG-SFDA) [PDF] [G-Scholar]
... [Zhong et al., Proc. ICIP 2023] Unknown class feature transformation for open set domain adaptation without source data [PDF] [G-Scholar--]
... [Li et al., Proc. ICIP 2023] Target-discriminability-induced multi-source-free domain adaptation [PDF] [G-Scholar--]
PaCDA [Prasanna B et al., Proc. CVPR Workshops 2023] Continual domain adaptation through pruning-aided domain-specific weight modulation [PDF] [G-Scholar] [CODE]
... [Yeh et al., Proc. ICCV Workshops 2023] Misalignment-free relation aggregation for multi-source-free domain adaptation [PDF] [G-Scholar--]
FCDA [Lee and Lee, Proc. SPIE International Workshop on Advanced Imaging Technology 2023] A source-free unsupervised domain adaptation method based on feature consistency [PDF] [G-Scholar]
... [Zhang et al., Proc. DSAA 2023] Tackling model mismatch with mixup regulated test-time training [PDF] [G-Scholar--]
FuzUMSFDA [Li et al., Proc. FUZZ 2023] Attention-bridging TS fuzzy rules for universal multi-domain adaptation without source data [PDF] [G-Scholar--]
CDT [Chen et al., Proc. PRCV 2023] Classifier decoupled training for black-box unsupervised domain adaptation [PDF] [G-Scholar--]
... [He et al., Proc. IEIR 2023] Robust batch relation preserving for lifelong unsupervised domain adaptation [PDF] [G-Scholar--]
GILL [Liang, Proc. ICCWAMTIP 2023] Source free domain adaptation based on latent dirichlet allocation [PDF] [G-Scholar--]
NRC++ [Yang et al., IEEE TPAMI 2023] Trust your good friends: Source-free domain adaptation by reciprocal neighborhood clustering [PDF] [G-Scholar]
TPDS [Tang et al., IJCV 2023] Source-free domain adaptation via target prediction distribution searching [PDF] [G-Scholar] [CODE]
SQAdapt [Li et al., IEEE TNNLS 2023] Source-free active domain adaptation via augmentation-based sample query and progressive model adaptation [PDF] [G-Scholar]
SDG-MA [Xu et al., IEEE TGRS 2023] Universal domain adaptation for remote sensing image scene classification [PDF] [G-Scholar] [CODE]

~~[Xu et al., Proc. IGARSS 2022] Universal domain adaptation without source data for remote sensing image scene classification [PDF] [G-Scholar]~~
ConDA [Taufique et al., IEEE TAI 2023] Continual unsupervised domain adaptation in data-constrained environments [PDF] [G-Scholar]

~~[Taufique et al., arXiv 2021] ConDA: Continual unsupervised domain adaptation [PDF]~~
SF-FDN [Li et al., IEEE TFS 2023] Source-free multi-domain adaptation with fuzzy rule-based deep neural networks [PDF] [G-Scholar]
PSAT-GDA [Tang et al., IEEE TMM 2023] Progressive source-aware transformer for generalized source-free domain adaptation [PDF] [G-Scholar--] [Code--]
TagSHOT [Hu et al., IEEE TMM 2023] Unleashing knowledge potential of source hypothesis for source-free domain adaptation [PDF] [G-Scholar--]
ASOGE [Cui et al., IEEE TCSVT 2023] Adversarial source generation for source-free domain adaptation [PDF] [G-Scholar--]
DCL [Tian et al., IEEE TCSVT 2023] DCL: Dipolar confidence learning for source-free unsupervised domain adaptation [PDF] [G-Scholar--]
PS [Du et al., Machine Learning 2023] Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation [PDF] [G-Scholar]
ProxyMix [Ding et al., Neural Networks 2023] ProxyMix: Proxy-based mixup training with label refinery for source-free domain adaptation [PDF] [G-Scholar] [CODE]
FAUST [Lee and Lee, Neural Networks 2023] Feature alignment by uncertainty and self-training for source-free unsupervised domain adaptation [PDF] [G-Scholar]
BPDA [Shi et al., Pattern Recognition 2023] Source-free and black-box domain adaptation via distributionally adversarial training [PDF] [G-Scholar] [CODE]
CPD [Zhou et al., Pattern Recognition 2023] Source-free domain adaptation with class prototype discovery [PDF] [G-Scholar]
UC-SFDA [Chen et al., Knowledge-Based Systems 2023] UC-SFDA: Source-free domain adaptation via uncertainty prediction and evidence-based contrastive learning [PDF] [G-Scholar] [CODE]
BIAS [Wang et al., Knowledge-Based Systems 2023] BIAS: Bridging inactive and active samples for active source free domain adaptation [PDF] [G-Scholar--]
CRMA [Lü et al., Expert Systems With Applications 2023] Consistency regularization-based mutual alignment for source-free domain adaptation [PDF] [G-Scholar--]
MSF-SSDA-SPM [Liang et al., Cognitive Neurodynamics 2023] Privacy-preserving multi-source semi-supervised domain adaptation for seizure prediction [PDF] [G-Scholar--]
RS2L [Tian et al., Signal, Image and Video Processing 2023] Robust self-supervised learning for source-free domain adaptation [PDF] [G-Scholar]
... [Zhao and Wang, Applied Intelligence 2023] Universal model adaptation by style augmented open-set consistency [PDF] [G-Scholar]
MViT-PCD [Dai et al., IEEE Geoscience and Remote Sensing Letters 2023] MViT-PCD: A lightweight ViT-based network for martian surface topographic change detection [PDF] [G-Scholar] [CODE]
OKRA [Zhao et al., Computers and Electrical Engineering 2023] Open-set black-box domain adaptation for remote sensing image scene classification [PDF] [G-Scholar--]
FMAS [Tian and Zhang, Computers and Electrical Engineering 2023] Feature mixing and self-training for source-free active domain adaptation [PDF] [G-Scholar--]
BCSW [Tian and Zhao, IEEE Geoscience and Remote Sensing Letters 2023] Source-free unsupervised domain adaptation via bi-classifier confidence score weighting [PDF] [G-Scholar--]
CLCR [Tang et al., CAAI Transactions on Intelligence Technology 2023] Model adaptation via credible local context representation [PDF] [G-Scholar--]
LCAL [Fan et al., Journal of Software 2023] Local consistent active learning for source free open-set domian adaptation [PDF] [G-Scholar]
... [Sahay et al., Sensors 2023] On the importance of attention and augmentations for hypothesis transfer in domain adaptation and generalization [PDF] [G-Scholar]
SIE [Chen et al., Machine Vision and Applications 2023] Two-stage structural information enhancement for source-free domain adaptation [PDF] [G-Scholar]
Um2B [Wang et al., Image and Vision Computing 2023] Universal domain adaptation from multiple black-box sources [PDF] [G-Scholar--]
FCDC [Wang et al., Chinese Journal Of Engineering Mathematics 2023] Source Free Domain Adaptation Based on Feature Structure [PDF] [G-Scholar--]
ALT [Wu et al., arXiv 2023] When source-free domain adaptation meets label propagation [PDF] [G-Scholar]
CaC [Chen et al., arXiv 2023] Contrast and clustering: Learning neighborhood pair representation for source-free domain adaptation [PDF] [G-Scholar] [CODE]
GarDA [Chen et al., arXiv 2023] Generative appearance replay for continual unsupervised domain adaptation [PDF] [G-Scholar]
PCD [Tanwisuth et al., arXiv 2023] A prototype-oriented clustering for domain shift with source privacy [PDF] [G-Scholar]
SCA [Maracani et al., arXiv 2023] Key design choices for double-transfer in source-free unsupervised domain adaptation [PDF] [G-Scholar]
... [Lee et al., arXiv 2023] Few-shot fine-tuning is all you need for source-free domain adaptation [PDF] [G-Scholar]
... [Rafiee et al., arXiv 2023] Source-free domain adaptation requires penalized diversity [PDF] [G-Scholar]
T-CPGA [Lin et al., arXiv 2023] Imbalance-agnostic source-free domain adaptation via avatar prototype alignment [PDF]) [G-Scholar]
Proto-SF-OSDA [Vray et al., arXiv 2023] Source-free open-set domain adaptation for histopathological images via distilling self-supervised vision transformer [PDF] [G-Scholar] [CODE--]
FREEDOM [Yang et al., arXiv 2023] FREEDOM: Target label & source data & domain information-free multi-source domain adaptation for unsupervised personalization [PDF] [G-Scholar]
CCT [Yan et al., arXiv 2023] Universal semi-supervised model adaptation via collaborative consistency training [PDF] [G-Scholar]
... [Yu et al., arXiv 2023] Open-set domain adaptation with visual-language foundation models [PDF] [G-Scholar]
... [Tang et al., arXiv 2023] Consistency regularization for generalizable source-free domain adaptation [PDF] [G-Scholar]
CABB [Jahan and Savakis, arXiv 2023] Curriculum guided domain adaptation in the dark [PDF] [G-Scholar]
TriDA [Xu et al., arXiv 2023] Incorporating pre-training data matters in unsupervised domain adaptation [PDF] [G-Scholar]
DAD++ [Nayak et al., arXiv 2023] DAD++: Improved data-free test time adversarial defense [PDF] [G-Scholar]
FM-SFDA [Chopra et al., arXiv 2023] Transcending domains through text-to-image diffusion: A source-free approach to domain adaptation [PDF] [G-Scholar]
SIDE [Liu et al., arXiv 2023] SIDE: Self-supervised intermediate domain exploration for source-free domain adaptation [PDF] [G-Scholar--] [CODE]
Cross DRI [Sawhney et al., arXiv 2023] Improving source-free target adaptation with vision transformers leveraging domain representation images [PDF] [G-Scholar]
HCLD [Liu et al., arXiv 2023] UFDA: Universal federated domain adaptation with practical assumptions [PDF] [G-Scholar]
... [Sheng et al., arXiv 2023] Self-training solutions for the ICCV 2023 GeoNet challenge [PDF] [G-Scholar]
E2 [Shen et al., Misc 2023] E2: Entropy discrimination and energy optimization for source-free universal domain adaptation [PDF] [G-Scholar]
... [Wang et al., Misc 2023] Graph-guided unsupervised clustering for source-free domain adaptation [PDF] [G-Scholar--]
... [Xiao et al., Misc 2023] Unified multi-level neighbor clustering for source-free unsupervised domain adaptation [PDF] [G-Scholar--]
... [Wong., Master Thesis 2023] Reducing negative transfer of random data in source-free unsupervised domain adaptation [PDF] [G-Scholar--]
... [Thomas., Master Thesis 2023] Continual domain adaptation through knowledge distillation [PDF] [G-Scholar--]

2024

SF(DA)$^2$ [Hwang et al., Proc. ICLR 2024] SF(DA)$^2$: Source-free domain adaptation through the lens of data augmentation [PDF] [G-Scholar] [CODE]
VDPG [Chi et al., Proc. ICLR 2024] Adapting to distribution shift by visual domain prompt generation [PDF] [G-Scholar] [CODE]
LEAD [Qu et al., Proc. CVPR 2024] LEAD: Learning decomposition for source-free universal domain adaptation [PDF] [G-Scholar] [CODE]
DPC [Xia et al., Proc. CVPR 2024] Discriminative pattern calibration mechanism for source-free domain adaptation [PDF] [G-Scholar--]
UPUK [Wan et al., Proc. CVPR 2024] Unveiling the unknown: Unleashing the power of unknown to known in open-set source-free domain adaptation [PDF] [G-Scholar--] [CODE--]
Improved SFDA [Mitsuzumi et al., Proc. CVPR 2024] Understanding and improving source-free domain adaptation from a theoretical perspective [PDF] [G-Scholar]
DCPL [Diamant et al., Proc. ECCV 2024] De-confusing pseudo-labels in source-free domain adaptation [PDF] [G-Scholar] [CODE]
NBF [Song et al., Proc. ECCV 2024] Is user feedback always informative? Retrieval latent defending for semi-supervised domain adaptation without source data [PDF] [G-Scholar] [CODE--]
LFTL [Lyu et al., Proc. ECCV 2024] Learn from the learnt: Source-free active domain adaptation via contrastive sampling and visual persistence [PDF] [G-Scholar] [CODE--]
FedGM [Wei and Han, Proc. AAAI 2024] Multi-source collaborative gradient discrepancy minimization for federated domain generalization [PDF] [G-Scholar] [CODE]
Bi-ATEN [Li et al, Proc. AAAI 2024] Agile multi-source-free domain adaptation [PDF [G-Scholar] [CODE]
SEAL [Xia et al, Proc. AAAI 2024] A separation and alignment framework for black-box domain adaptation [PDF [G-Scholar--] [CODE]
RFC [Zhang et al, Proc. AAAI 2024] Reviewing the forgotten classes for domain adaptation of black-box predictors [PDF [G-Scholar] [CODE]
DMP [Zhan et al, Proc. IJCAI 2024] Towards dynamic-prompting collaboration for source-free domain adaptation [PDF [G-Scholar--]
AEM [Xiao et al., Proc. ACM MM 2024] Adversarial experts model for black-box domain adaptation [PDF] [G-Scholar--]
... [Shen et al., Proc. AISTATS 2024] Continual domain adversarial adaptation via double-head discriminators [PDF] [G-Scholar]
EIANet [Pan et al., Proc. BMVC 2024] EIANet: A novel domain adaptation approach to maximize class distinction with neural collapse principles [PDF] [G-Scholar] [CODE]
C-SFTrans [Sanyal et al., Proc. WACV 2024] Aligning non-causal factors for transformer-based source-free domain adaptation [PDF] [G-Scholar] [CODE]
CXDA [Bohdal et al., Proc. WACV 2024] Feed-forward latent domain adaptation [PDF] [G-Scholar]
COCA [Liu et al., Proc. ACCV 2024] COCA: Classifier-oriented calibration via textual prototype for source-free universal domain adaptation [PDF] [G-Scholar] [CODE]

~~ [Bohdal et al., Proc. ICML Workshops 2022] Feed-forward source-free latent domain adaptation via cross-attention [PDF] [G-Scholar]~~
USD [Jahan and Savakis, Proc. CVPR Workshops 2023] Unknown sample discovery for source free open set domain adaptation [PDF] [G-Scholar]
UAD [Sivaprasad and Fleuret, Proc. ISBI 2024] Multi-source-free domain adaptation via uncertainty-aware adaptive distillation [PDF] [G-Scholar]
SADA [Liu et al., Proc. ICME 2024] SADA: Self-adaptive domain adaptation from black-box predictors [PDF] [G-Scholar]
PECAL [Machireddy et al., Proc. ICIP 2024] Source-free continual adaptive learning with limited labels on evolving data drifts [PDF] [G-Scholar--]
... [Banerjee and Ganesh, Proc. ICPR 2024] Real-world coarse to fine-grained source-free multidomain adaptation [PDF] [G-Scholar]
CAT^3 [Feng et al., Proc. CAI 2024] Category-aware test-time training domain adaptation [PDF] [G-Scholar]
... [Chen et al., Proc. PRCV 2024] An entropy-based pseudo-label mixup method for source-free domain adaptation [PDF] [G-Scholar]
SMOTE [Zou et al., Proc. VCIP 2024] Handling class imbalance in black-box unsupervised domain adaptation with synthetic minority over-sampling [PDF] [G-Scholar--]
FedAcross [Röder et al., Proc. ICPRAM 2024] Crossing domain borders with federated few-shot adaptation [PDF] [G-Scholar]
... [Yang et al., Proc. IEEE CSCWD 2024] Source free domain adaptation via adapting to the enhanced style [PDF] [G-Scholar--]
k-sBetas [Chiaroni et al., IEEE TPAMI 2024] Simplex clustering via sBeta with applications to online adjustment of black-box predictions [PDF] [G-Scholar] [CODE]
EAAF [Pei et al., IEEE TPAMI 2024] Evidential multi-source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
CC-Loss [Jin et al., IEEE TPAMI 2024] One fits many: Class confusion loss for versatile domain adaptation [PDF] [G-Scholar] [CODE]
Co-learn++ [Zhang et al., IJCV 2024] Source-free domain adaptation guided by vision and vision-language pre-training [PDF] [G-Scholar]
BMD-v2 [Qu et al., IJCV 2024] General Class-balanced multicentric dynamic prototype pseudo-labeling for source-free domain adaptation [PDF] [G-Scholar--] [CODE]
ASM [Jing et al., IEEE TIP 2024] Visually source-free domain adaptation via adversarial style matching [PDF] [G-Scholar]
ICPR [Tian et al., IEEE TNNLS 2024] Intrinsic consistency preservation with adaptively reliable samples for source-free domain adaptation [PDF] [G-Scholar] [CODE]
NAMI [Zhang et al., IEEE TMM 2024] Neighborhood-aware mutual information maximization for source-free domain adaptation [PDF] [G-Scholar--]
... [Ma et al., IEEE TCSVT 2024] Exploring relational knowledge for source-free domain adaptation [PDF] [G-Scholar--]
SFADA [He et al., Pattern Recognition 2024] Source-free domain adaptation with unrestricted source hypothesis [PDF] [G-Scholar] [CODE]
DPLS [Ma et al., Pattern Recognition 2024] Source-free domain adaptation via dynamic pseudo labeling and self-supervision [PDF] [G-Scholar] [CODE]
GOAL [Peng et al., Pattern Recognition 2024] Global self-sustaining and local inheritance for source-free unsupervised domain adaptation [PDF] [G-Scholar]
PFC [Pan et al., Pattern Recognition 2024] Overcoming learning bias via prototypical feature compensation for source-free domain adaptation [PDF] [G-Scholar]
GDT [Tian and Zhao, Neural Networks 2024] Generation, division and training: A promising method for source-free unsupervised domain adaptation [PDF] [G-Scholar]
SS-TrBoosting [Deng et al., IEEE TAI 2024] Semi-supervised transfer boosting (SS-TrBoosting) [PDF] [G-Scholar]
SiLAN [Wang et al., TMLR 2024] What has been overlooked in contrastive source-free domain adaptation: Leveraging source-informed latent augmentation within neighborhood context [PDF] [G-Scholar--] [CODE]
UPA [Chen et al., Neurocomputing 2024] Uncertainty-aware pseudo-label filtering for source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
... [Xing et al., Neurocomputing 2024] Rectifying self-training with neighborhood consistency and proximity for source-free domain adaptation [PDF] [G-Scholar] [CODE]
... [Wang et al., Neurocomputing 2024] Robust source-free domain adaptation with anti-adversarial samples training [PDF] [G-Scholar]
CdKC [Zhang et al., Information Processing & Management 2024] Cross-domain knowledge collaboration for blending-target domain adaptation [PDF] [G-Scholar--]
HCDA [Li et al., Pattern Recognition Letters 2024] Pseudo-label refinement via hierarchical contrastive learning for source-free unsupervised domain adaptation [PDF] [G-Scholar]
... [Zhou et al., Pattern Recognition Letters 2024] Multi source-free domain adaptation based on pseudo-label knowledge mining [PDF] [G-Scholar]
DCA [Wang et al., Neural Processing Letters 2024] Dual classifier adaptation: Source-free UDA via adaptive pseudo-labels learning [PDF] [G-Scholar--] [CODE]
CODA [Liu et al., Engineering Applications of Artificial Intelligence 2024] Consistency-guided multi-source-free domain adaptation [PDF] [G-Scholar--]
SCAL [Sun et al., IET Image Processing 2024] You only label once: A self-adaptive clustering-based method for source-free active domain adaptation [PDF] [G-Scholar]
FUSE [Tian et al., Signal, Image and Video Processing 2024] Source bias reduction for source-free domain adaptation [PDF] [G-Scholar--]
TAS [Shao et al., Neural Computing and Applications 2024] Adaptive pseudo-label threshold for source-free domain adaptation [PDF] [G-Scholar--]
RECS [Tian and Sun, Neural Computing and Applications 2024] Rethinking confidence scores for source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
MLCL [Ouyang et al., Multimedia Systems 2024] Exploiting multi-level consistency learning for source-free domain adaptation [PDF] [G-Scholar] [CODE]
SP-CDL [Santoso and Wijaya, Asian American Research Letters Journal 2024] Source-private cross-domain learning: Enhancing visual recognition with multi-source domain adaptation [PDF] [G-Scholar]
USDAP [Shao et al., Journal of Electronic Imaging 2024] USDAP: universal source-free domain adaptation based on prompt learning [PDF] [G-Scholar--]
CosGAN [Naz et al., Intelligent Automation & Soft Computing 2024] Robot vision over CosGANs to enhance performance with source-free domain adaptation using advanced loss function [PDF] [G-Scholar--]
MixAdapt [Sheng et al., arXiv 2024] Can we trust the unlabeled target data? Towards backdoor attack and defense on model adaptation [PDF] [G-Scholar]
4Ds [Tang et al., arXiv 2024] Direct distillation between different domains [PDF] [G-Scholar]
DM-SFDA [Chopra et al., arXiv 2024] Source-free domain adaptation with diffusion-guided source data generation [PDF] [G-Scholar]
SepRep-Net [Jin et al., arXiv 2024] SepRep-Net: Multi-source free domain adaptation via model separation and reparameterization [PDF] [G-Scholar]
LDAuCID [Rostami, arXiv 2024] Continuous unsupervised domain adaptation using stabilized representations and experience replay [PDF] [G-Scholar] [CODE]
HCPR [Shu et al., arXiv 2024] Source-free unsupervised domain adaptation with hypothesis consolidation of prediction rationale [PDF] [G-Scholar] [CODE]
SCA [Maracani et al., arXiv 2024] Key design choices in source-free unsupervised domain adaptation: An in-depth empirical analysis [PDF] [G-Scholar]
SUTE [Pei et al., arXiv 2024] On the model-agnostic multi-source-free unsupervised domain adaptation [PDF] [G-Scholar]
LCFD [Tang et al., arXiv 2024] Unified source-free domain adaptation [PDF] [G-Scholar] [CODE]
GLC++ [Qu et al., arXiv 2024] GLC++: Source-free universal domain adaptation through global-local clustering and contrastive affinity learning [PDF] [G-Scholar] [CODE]
... [Litrico et al., arXiv 2024] Uncertainty-guided open-set source-free unsupervised domain adaptation with target-private class segregation [PDF] [G-Scholar]
... [Zou et al., arXiv 2024] Incremental pseudo-labeling for black-box unsupervised domain adaptation [PDF] [G-Scholar]
... [Jiang et al., arXiv 2024] High-order neighborhoods know more: HyperGraph learning meets source-free unsupervised domain adaptation [PDF] [G-Scholar]
MIRoUDA [Yin et al., arXiv 2024] Towards trustworthy unsupervised domain adaptation: A representation learning perspective for enhancing robustness, discrimination, and generalization [PDF] [G-Scholar--]
ECA [Zheng et al., arXiv 2024] Evidential graph contrastive alignment for source-free blending-target domain adaptation [PDF] [G-Scholar]
TAB [Maracani et al., arXiv 2024] Trust and balance: Few trusted samples pseudo-labeling and temperature scaled loss for effective source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE--]
StepSPT [Xu et al., arXiv 2024] Step-wise distribution alignment guided style prompt tuning for source-free cross-domain few-shot learning [PDF] [G-Scholar] [CODE]
MEA [Wang et al., arXiv 2024] Unveiling the superior paradigm: A comparative study of source-free domain adaptation and unsupervised domain adaptation [PDF] [G-Scholar]
RRDA [Nejjar et al., arXiv 2024] Recall and refine: A simple but effective source-free open-set domain adaptation framework [PDF] [G-Scholar] [CODE]
ProDDing [Liang et al., arXiv 2024] Prototypical distillation and debiased tuning for black-box unsupervised domain adaptation [PDF] [G-Scholar]
... [Zhu et al., Misc 2024] Pick and adapt: An iterative approach for source-free domain adaptation [PDF] [G-Scholar--]
SlimTTT [Cai et al., Misc 2024] Resource efficient test-time training with slimmable network [PDF] [G-Scholar--]
LPR [Yoo et al., Misc 2024] Label space-induced pseudo label refinement for multi-source black-box domain adaptation [PDF] [G-Scholar--]
... [Musabe, Master Thesis 2024] Towards regression-free and source-free online domain adaptation [PDF] [G-Scholar]
... [Eastwood, Phd Thesis 2024] Shift happens: How can machine learning systems be best prepared? [PDF] [G-Scholar--]
... [Chhabra, Phd Thesis 2024] Making the best of what we have: Novel strategies for training neural networks under restricted labeling information [PDF] [G-Scholar--]
... [Yuan, Phd Thesis 2024] Domain adaptation in biomedical engineering: unsupervised, source‑free, and black box approaches [PDF] [G-Scholar--]

2025

ProDe [Tang et al., Proc. ICLR 2025] Proxy denoising for source-free domain adaptation [PDF] [G-Scholar]
UCon-SFDA [Xu et al., Proc. ICLR 2025] Revisiting source-free domain adaptation: A new perspective via uncertainty control [PDF] [G-Scholar--] [CODE--]
GMM [Schlachter et al., Proc. WACV 2025] Memory-efficient pseudo-labeling for online source-free universal domain adaptation using a gaussian mixture model [PDF] [G-Scholar] [CODE]
EKS [Rai et al., Proc. WACV 2025] Label calibration in source free domain adaptation [PDF] [G-Scholar] [CODE--]
NVC-LLN [Xu et al., IEEE TPAMI 2025] Unraveling the mysteries of label noise in source-free domain adaptation: Theory and practice [PDF] [G-Scholar] [CODE]

Attacks and Defenses

AdaptGuard [Sheng et al., Proc. ICCV 2023] AdaptGuard: Defending against universal attacks for model adaptation [PDF] [G-Scholar]
MIXADAPT [Sheng et al., arXiv 2024] Can we trust the unlabeled target data: Towards backdoor attack and defense on model adaptation [PDF] [G-Scholar]

Semantic Segmentation

2021

SFDA-UR [Sivaprasad and Fleuret, Proc. CVPR 2021] Uncertainty reduction for model adaptation in semantic segmentation [PDF] [G-Scholar] [CODE]
SFDA-KTMA [Liu et al., Proc. CVPR 2021] Source-free domain adaptation for semantic segmentation [PDF] [G-Scholar]
SoMAN-cPAE [Kundu et al., Proc. ICCV 2021] Generalize then adapt: Source-free domain adaptive semantic segmentation [PDF] [G-Scholar] [CODE]
MAS3 [Stan and Rostami, Proc. AAAI 2021] Unsupervised model adaptation for continual semantic segmentation [PDF] [G-Scholar] [CODE]
LD [You et al., Proc. ACMMM 2021] Domain adaptive semantic segmentation without source data [PDF] [G-Scholar] [CODE]
SFDA-VS [Ye et al., Proc. ACMMM 2021] Source data-free unsupervised domain adaptation for semantic segmentation [PDF] [G-Scholar]
AUGCO [Prabhu et al., Proc. NeurIPS Workshops 2022] Augmentation consistency-guided self-training for source-free domain adaptive semantic segmentation [PDF] [G-Scholar]

~~[Prabhu et al., Proc. ECCV Workshops 2022] AUGCO: Augmentation consistency-guided self-training for source-free domain adaptive semantic segmentation [PDF]~~

~~[Prabhu et al., arXiv 2021] S4T: Source-free domain adaptation for semantic segmentation via self-supervised selective self-training [PDF]~~
PR-SFDA [Luo et al., arXiv 2021] Exploiting negative learning for implicit pseudo label rectification in source-free domain adaptive semantic segmentation [PDF] [G-Scholar]
SFDA-ST [Paul et al., arXiv 2021] Unsupervised adaptation of semantic segmentation models without source data [PDF] [G-Scholar]

2022

RIPU [Xie et al., Proc. CVPR 2022] Towards fewer annotations: Active learning via region impurity and prediction uncertainty for domain adaptive semantic segmentation [PDF] [G-Scholar] [CODE]
SimT [Guo et al., Proc. CVPR 2022] SimT: Handling open-set noise for domain adaptive semantic segmentation [PDF] [G-Scholar] [CODE]
OnDA [Panagiotakopoulos et al., Proc. ECCV 2022] Online domain adaptation for semantic segmentation in ever-changing conditions [PDF] [G-Scholar] [CODE]
UnMSMA-MiFL [Li et al., Proc. ECCV 2022] Union-set multi-source model adaptation for semantic segmentation [PDF] [G-Scholar] [CODE]
UBNA [Klingner et al., Proc. WACV Workshops 2022] Unsupervised batchnorm adaptation (ubna): A domain adaptation method for semantic segmentation without using source domain representations [PDF] [G-Scholar] [CODE]
DTAC [Yang et al., Proc. ICME 2022] Source free domain adaptation for semantic segmentation via distribution transfer and adaptive class-balanced self-training [PDF] [G-Scholar]
MSMA-MiFL [Li et al., Proc. ICIP 2022] Improving model adaptation for semantic segmentation by learning model-invariant features with multiple source-domain models [PDF] [G-Scholar]
SPGM [Yang et al., IEEE TIFS 2022] Revealing task-relevant model memorization for source-protected unsupervised domain adaptation [PDF] [G-Scholar]
CPSS [Zhao et al., IEEE TCSVT 2022] Source-free open compound domain adaptation in semantic segmentation [PDF] [G-Scholar] [CODE]
RuST [Luo et al., IEEE RAL 2022] Multi-level consistency learning for source-free model adaptation [PDF] [G-Scholar]
STvM [Akkaya et al., arXiv 2022] Self-training via metric learning for source-free domain adaptation of semantic segmentation [PDF] [G-Scholar]
CONDA [Truong et al., arXiv 2022] CONDA: Continual unsupervised domain adaptation learning in visual perception for self-driving cars [PDF] [G-Scholar]

2023

Uni-UVPT [Ma et al., Proc. NeurIPS 2023] When visual prompt tuning meets source-free domain adaptive semantic segmentation [PDF] [G-Scholar]
STPL [Lo et al., Proc. CVPR 2023] Spatio-temporal pixel-level contrastive learning-based source-free domain adaptation for video semantic segmentation [PDF] [G-Scholar]
DT-ST [Zhao et al., Proc. CVPR 2023] Towards better stability and adaptability: Improve online self-training for model adaptation in semantic segmentation [PDF] [G-Scholar]
... [Lo et al., Proc. CVPR 2023] Unsupervised continual semantic adaptation through neural rendering [PDF] [G-Scholar]
... [Yin et al., Proc. ICCV 2023] CrossMatch: Source-free domain adaptive semantic segmentation via cross-modal consistency training [PDF] [G-Scholar--]
Cal-SFDA [Wang et al., Proc. ACMMM 2023] Cal-SFDA: Source-free domain-adaptive semantic segmentation with differentiable expected calibration error [PDF] [G-Scholar] [CODE]
... [Li et al., Proc. ACMMM 2023] When masked image modeling meets source-free unsupervised domain adaptation: Dual-level masked network for semantic segmentation [PDF] [G-Scholar--]
... [Bohdal et al., Proc. ICLR Workshops 2023] Label calibration for semantic segmentation under domain shift [PDF] [G-Scholar]
CoRTe [Cuttano et al., Proc. ICCV Workshops 2023] Cross-domain transfer learning with CoRTe: Consistent and reliable transfer from black-box to lightweight segmentation model [PDF] [G-Scholar]

CROTS [Luo et al., IJCV 2023] Crots: Cross-domain teacher–student learning for source-free domain adaptive semantic segmentation [PDF] [G-Scholar] [CODE--]
... [Lu et al., IEEE TIP 2023] Uncertainty-aware source-free domain adaptive semantic segmentation [PDF] [G-Scholar]
STAL [Guan and Yuan, arXiv 2023] Iterative loop learning combining self-training and active learning for domain adaptive semantic segmentation [PDF] [G-Scholar] [CODE]
BTOL [Wang et al., arXiv 2023] Bootstrap the original latent: Freeze-and-thaw adapter for back-propagated black-box adaptation [PDF] [G-Scholar]
CMA [Bruggemann et al., arXiv 2023] Contrastive model adaptation for cross-condition robustness in semantic segmentation [PDF] [G-Scholar] [CODE]
CoSDA [Feng et al., arXiv 2023] CoSDA: Continual source-free domain adaptation [PDF] [G-Scholar] [CODE]
IAPC [Cao et al., arXiv 2023] Towards source-free domain adaptive semantic segmentation via importance-aware and prototype-contrast learning [PDF] [G-Scholar] [CODE]
PTDiffSeg [Gong et al., arXiv 2023] Prompting diffusion representations for cross-domain semantic segmentation [PDF] [G-Scholar] [CODE--]
ReGEN [Tjio et al., arXiv 2023] Generating reliable pixel-level labels for source free domain adaptation [PDF] [G-Scholar]
WeSAM [Zhang et al., arXiv 2023] Improving the generalization of segmentation foundation model under distribution shift via weakly supervised adaptation [PDF] [G-Scholar] [CODE]
... [Sashikanth., Master Thesis 2023] Active learning guided source-free domain adaptive semantic segmentation and applications in the environmental space [PDF] [G-Scholar]

2024

360SFUDA [Zheng et al., Proc. CVPR 2024] Semantics, distortion, and style matter: Towards source-free UDA for panoramic segmentation [PDF] [G-Scholar] [CODE]
SND [Zhao et al., Proc. CVPR 2024] Stable neighbor denoising for source-free domain adaptive segmentation [PDF] [G-Scholar] [CODE]
FREST [Lee et al, Proc. ECCV 2024] FREST: Feature restoration for semantic segmentation under multiple adverse conditions [PDF] [G-Scholar] [CODE--]
RKP [Zang et al., Proc. ACM MM 2024] Generalized source-free domain-adaptive segmentation via reliable knowledge propagation [PDF] [G-Scholar--]
... [Gao et al., Proc. IEEE GRSL 2024] Attention prompt-driven source-free adaptation for remote sensing images semantic segmentation [PDF] [G-Scholar]
ATP [Wang et al., IEEE TPAMI 2024] A curriculum-style self-training approach for source-free semantic segmentation [PDF] [G-Scholar] [CODE]

~~ATP [Wang et al., arXiv 2021] Source data-free cross-domain semantic segmentation: align, teach and propagate [PDF] [G-Scholar]~~
PIG [Xie et al., IEEE TIP 2024] PIG: Prompt images guidance for night-time scene parsing [PDF] [G-Scholar] [CODE]
ProAC [Ren et al., IEEE TCSVT 2024] Exploring prototype-anchor contrast for semantic segmentation [PDF] [G-Scholar]
... [Tian et al., IEEE TMM 2024] Self-mining the confident prototypes for source-free unsupervised domain adaptation in image segmentation [PDF] [G-Scholar]
... [Ren et al., Multimedia Systems 2024] SAM-guided contrast based self-training for source-free cross-domain semantic segmentation [PDF] [G-Scholar--]
... [Zhou et al., Image and Vision Computing 2024] Black-box model adaptation for semantic segmentation [PDF] [G-Scholar--]
... [Stand and Rostami, Frontiers in Big Data 2024] Source-free domain adaptation for semantic image segmentation using internal representations [PDF] [G-Scholar--]
MAS3 [Stan and Rostami, arXiv 2024] Online continual domain adaptation for semantic image segmentation using internal representations [PDF] [G-Scholar]
FFreeDA [Rizzoli et al., arXiv 2024] When cars meet drones: Hyperbolic federated learning for source-free domain adaptation in adverse weather [PDF] [G-Scholar]
360SFUDA++ [Zheng et al., arXiv 2024] 360SFUDA++: Towards source-free UDA for panoramic segmentation by learning reliable category prototypes [PDF] [G-Scholar] [CODE]

Object Detection

before 2020

DA-Re2 [Jamal et al., Proc. CVPR 2018] Deep face detector adaptation without negative transfer or catastrophic forgetting [PDF] [G-Scholar]
TemporalST [RoyChowdhury et al., Proc. CVPR 2019] Automatic adaptation of object detectors to new domains using self-training [PDF] [G-Scholar] [CODE]

2021

SFOD-Mosaic [Li et al., Proc. AAAI 2021] A free lunch for unsupervised domain adaptive object detection without source data [PDF] [G-Scholar]
SMT [Zhang et al., Proc. ACMMM Asia 2021] Source-style transferred mean teacher for source-data free object detection [PDF] [G-Scholar]
SOAP [Xiong et al., International Journal of Intelligent Systems 2021] Source data‐free domain adaptation of object detector through domain‐specific perturbation [PDF] [G-Scholar]

2022

SFDA-PT [Chen et al., Proc. ICML 2022] Learning domain adaptive object detection with probabilistic teacher [PDF] [G-Scholar] [CODE]
LODS [Li et al., Proc. CVPR 2022] Source-free object detection by learning to overlook domain style [PDF] [G-Scholar] [CODE]
S&M [Yuan et al., Proc. ICASSP 2022] Simulation-and-mining: Towards accurate source-free unsupervised domain adaptive object detection [PDF] [G-Scholar]
PLMS [Tang et al., Proc. ICME 2022] Source-free unsupervised cross-domain pedestrian detection via pseudo label mining and screening [PDF] [G-Scholar]
MoTE [VS et al., Proc. ICIP 2022] Mixture of teacher experts for source-free domain adaptive object detection [PDF] [G-Scholar]
ESOD [Wei et al., Proc. ICONIP 2022] Entropy-minimization mean teacher for source-free domain adaptive object detection [PDF] [G-Scholar]
PLA-DAP [Xiong et al., Pattern Recognition 2022] Source data-free domain adaptation for a faster R-CNN [PDF] [G-Scholar] [CODE]
G&A [Zhao et al., arXiv 2022] 1st place solution for ECCV 2022 OOD-CV challenge object detection track [PDF] [G-Scholar]

2023

IRG [VS et al., Proc. CVPR 2023] Instance relation graph guided source-free domain adaptive object detection [PDF] [G-Scholar] [CODE]
PETS [Liu et al., Proc. ICCV 2023] Periodically exchange teacher-student for source-free object detection [PDF] [G-Scholar]
... [Chen et al., Proc. ACMMM 2023] Exploiting low-confidence pseudo-labels for source-free object detection [PDF] [G-Scholar]
TeST [Sinha et al., Proc. WACV 2023] TeST: Test-time self-training under distribution shift [PDF] [G-Scholar]
MemCLR [VS et al., Proc. WACV 2023] Towards online domain adaptive object detection [PDF] [G-Scholar]
RPL [Zhang et al., Proc. ICASSP 2023] Refined pseudo labeling for source-free domain adaptive object detection [PDF] [G-Scholar]
... [Lin et al., Proc. ICME 2023] Run and chase: Towards accurate source-free domain adaptive object detection [PDF] [G-Scholar]
... [Peng et al., Proc. ICANN 2023] Gradient adjusted and weight rectified mean teacher for source-free object detection [PDF] [G-Scholar]
SFDA-STW [Yang et al., IEEE TIM 2023] Source-free domain adaptive detection of concealed objects in passive millimeter-wave images [PDF] [G-Scholar]
MPG [Zhang et al., IEEE T-IV 2023] Multi-prototype guided source-free domain adaptive object detection for autonomous driving [PDF] [G-Scholar]
A2SFOD [Chu et al., arXiv 2023] Adversarial alignment for source free object detection [PDF] [G-Scholar]
... [Naik et al., arXiv 2023] Do machine learning models learn common sense? [PDF] [G-Scholar]
... [Sun et al., arXiv 2023] SF-FSDA: Source-free few-shot domain adaptive object detection with efficient labeled data factory [PDF] [G-Scholar]
... [Shi et al., arXiv 2023] Improving online source-free domain adaptation for object detection by unsupervised data acquisition [PDF] [G-Scholar]

2024

LPLD [Yoon et al., Proc. ECCV 2024] Enhancing source-free domain adaptive object detection with low-confidence pseudo-label distillation [PDF] [G-Scholar] [CODE]
DRU [Khanh et al., Proc. ECCV 2024] Dynamic retraining-updating mean teacher for source-free object detection [PDF] [G-Scholar] [CODE]
STAR-MT [Zhang and Zhou, Proc. CVPR Workshops 2024] Source-free domain adaptation for video object detection under adverse image conditions [PDF] [G-Scholar]
... [Liu et al., Proc. IGARSS 2024] CLIP-guided source-free object detection in aerial images [PDF] [G-Scholar]
S3AHI [Ding et al., Proc. IJCNN 2024] S3AHI: Source-free domain adaptive small object detection with slicing aided hyper inference [PDF] [G-Scholar--]
DACA [Zhao et al., IJCV 2024] Multi-source-free domain adaptive object detection [PDF] [G-Scholar]
... [Deng et al., IEEE TCSVT 2024] Balanced teacher for source-free object detection [PDF] [G-Scholar]
... [Liu et al., Geo-spatial Information Science 2024] Multi-level domain perturbation for source-free object detection in remote sensing images [PDF] [G-Scholar]
RMT [Tian et al., Alexandria Engineering Journal 2024] A relation-enhanced mean-teacher framework for source-free domain adaptation of object detection [PDF] [G-Scholar--]
... [Liu et al., arXiv 2024] Source-free domain adaptive object detection in remote sensing images [PDF] [G-Scholar]
... [Wei et al., The Journal of Supercomputing 2025] Proposal-level reliable feature-guided contrastive learning for SFOD [PDF] [G-Scholar]

Medical Image Analysis

2020

AdaEnt [Bateson et al., Proc. MICCAI 2020] Source-relaxed domain adaptation for image segmentation [PDF] [G-Scholar] [CODE]

2021

OSUDA [Liu et al., Proc. MICCAI 2021] Adapting off-the-shelf source segmenter for target medical image segmentation [PDF] [G-Scholar]
DPL [Chen et al., Proc. MICCAI 2021] Source-free domain adaptive fundus image segmentation with denoised pseudo-labeling [PDF] [G-Scholar] [CODE]

2022

MetaTeacher [Wang et al., Proc. NeurIPS 2022] Metateacher: Coordinating multi-model domain adaptation for medical image classification [PDF] [G-Scholar] [CODE]
SI-SFDA [Ye et al., Proc. ACMMM 2022] Alleviating style sensitivity then adapting: Source-free domain adaptation for medical image segmentation [PDF] [G-Scholar]
SDG-CMT [Zhu et al., Proc. BIBM 2022] Domain adaptation for medical image classification without source data [PDF] [G-Scholar]
SFS [Stan and Rostami, Proc. BMVC 2022] Domain adaptation for the segmentation of confidential medical images [PDF] [G-Scholar]
U-D4R [Xu et al., Proc. MICCAI 2022] Denoising for relaxing: Unsupervised domain adaptive fundus image segmentation without source data [PDF] [G-Scholar]
APL [Li et al., Proc. ICASSP 2022] Adaptive pseudo labeling for source-free domain adaptation in medical image segmentation [PDF] [G-Scholar]
CST [Xie et al., Proc. NeurIPS Workshops 2022] Learn complementary pseudo-label for source-free domain adaptive medical segmentation [PDF] [G-Scholar--]
FUSION [Chattopadhyay et al., Proc. ECCV Workshops 2022] FUSION: Fully unsupervised test-time stain adaptation via fused normalization statistics [PDF] [G-Scholar]
SMPT++ [Liu and Yuan, IEEE TMI 2022] A source-free domain adaptive polyp detection framework with style diversification flow [PDF] [G-Scholar] [CODE]
AdaMI [Bateson et al., Medical Image Analysis 2022] Source-free domain adaptation for image segmentation [PDF] [G-Scholar] [CODE]
MCOSUDA [Liu et al., Medical Image Analysis 2022] Memory consistent unsupervised off-the-shelf model adaptation for source-relaxed medical image segmentation [PDF] [G-Scholar]
SFDA-FSM [Yang et al., Medical Image Analysis 2022] Source free domain adaptation for medical image segmentation with fourier style mining [PDF] [G-Scholar] [CODE]
PPMSDA [Han et al., IEEE JBHI 2022] Privacy-preserving multi-source domain adaptation for medical data [PDF] [G-Scholar]
AOS [Hong et al., Knowledge-Based Systems 2022] Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation [PDF] [G-Scholar] [CODE]
PSMT [Wei et al., Journal of Supercomputing 2022] Source-free domain adaptive object detection based on pseudo-supervised mean teacher [PDF] [G-Scholar--]
BBUDA-EMD [Liu et al., Frontiers in Neuroscience 2022] Unsupervised black-box model domain adaptation for brain tumor segmentation [PDF] [G-Scholar]

~~[Liu et al., Proc. SPIE Medical Imaging 2022] Unsupervised domain adaptation for segmentation with black-box source model [PDF]~~
TT-SFUDA [VS et al., arXiv 2022] Target and task specific source-free domain adaptive image segmentation [PDF] [G-Scholar] [CODE]
SFDA-NS [Kondo, arXiv 2022] Source-free unsupervised domain adaptation with norm and shape constraints for medical image segmentation [PDF] [G-Scholar]
ProSFDA [Hu et al., arXiv 2022] ProSFDA: Prompt learning based source-free domain adaptation for medical image segmentation [PDF] [G-Scholar] [CODE]
IOP-FL [Jiang et al., arXiv 2022] IOP-FL: Inside-outside personalization for federated medical image segmentation [PDF] [G-Scholar]
SFDA-GEM [Yuan et al., Misc 2022] Source protection domain adaptation by gumbel-min-max entropy minimization [PDF] [G-Scholar]
PLP [Song, Misc 2022] Source-free few-shot semi-supervised domain adaptation for CT image classification [PDF] [G-Scholar]
... [Li et al., Misc 2022] Source-free unsupervised adaptive segmentation for knee joint MRI [PDF] [G-Scholar]

2023

SFHarmony [Dinsdale et al., Proc. ICCV 2023] SFHarmony: Source free domain adaptation for distributed neuroimaging analysis [PDF] [G-Scholar] [CODE]
SUMT [Wen et al., Proc. IPMI 2023] Source-free domain adaptation for medical image segmentation via selectively updated mean teacher [PDF] [G-Scholar]
UPL-TTA [Wu et al., Proc. IPMI 2023] UPL-TTA: Uncertainty-aware pseudo label guided fully test time adaptation for fetal brain segmentation [PDF] [G-Scholar]
RPANet [Wang and Chen, Proc. IPMI 2023] Unsupervised adaptation of polyp segmentation models via coarse-to-fine self-supervision [PDF] [G-Scholar]
CBMT [Tang et al., Proc. MICCAI 2023] Source-free domain adaptive fundus image segmentation with class-balanced mean teacher [PDF] [G-Scholar] [CODE]
ProtoContra [Yu et al., Proc. MICCAI 2023] Source-free domain adaptation for medical image segmentation via prototype-anchored feature alignment and contrastive learning [PDF] [G-Scholar] [CODE]
SaTTCA [Li et al., Proc. MICCAI 2023] Scale-aware test-time click adaptation for pulmonary nodule and mass segmentation [PDF] [G-Scholar] [CODE]
CPR [Huai et al., Proc. MICCAI 2023] Context-aware pseudo-label refinement for source-free domain adaptive fundus image segmentation [PDF] [G-Scholar] [CODE]
... [Wang et al., Proc. MICCAI 2023] Black-box domain adaptative cell segmentation via multi-source distillation [PDF] [G-Scholar] [CODE]
TGMA [Yang et al., Proc. MICCAI 2023] Transferability-guided multi-source model adaptation for medical image segmentation [PDF] [G-Scholar]
... [Lee et al., Proc. MICCAI 2023] Self-supervised domain adaptive segmentation of breast cancer via test-time fine-tuning [PDF] [G-Scholar]
... [Kondo, Proc. MICCAI Workshops 2023] Black-box unsupervised domain adaptation for medical image segmentationt [PDF] [G-Scholar]
... [Yuan et al., Proc. EMBC 2023] Entropy-driven adversarial training for source-free medical image segmentation [PDF] [G-Scholar]
MATS [Chen et al., Proc. MIDL 2023] Model adaptive tooth segmentation [PDF] [G-Scholar]
... [Wang et al., Proc. CMMCA 2023] Advancing delineation of gross tumor volume based on magnetic resonance imaging by performing source-free domain adaptation in nasopharyngeal carcinoma [PDF] [G-Scholar]
... [Zhang et al., Proc. ICCECE 2023] Source-free domain adaptation via multicentric prototype for alzheimer's disease detection [PDF] [G-Scholar--]
... [Xu et al., Proc. AI 2023] Cross domain pulmonary nodule detection without source data [PDF] [G-Scholar--]
... [Li et al., IEEE TMI 2023] Towards source-free cross tissues histopathological cell segmentation via target-specific finetuning [PDF] [G-Scholar] [CODE]
UPL-SFDA [Wu et al., IEEE TMI 2023] UPL-SFDA: Uncertainty-aware pseudo label guided source-free domain adaptation for medical image segmentation [PDF] [G-Scholar]
SAME [Li et al., IEEE TMI 2023] Enhancing and adapting in the clinic: Source-free unsupervised domain adaptation for medical image enhancement [PDF] [G-Scholar] [CODE]
DUT [Liu et al., IEEE TNNLS 2023] Decoupled unbiased teacher for source-free domain adaptive medical object detection [PDF] [G-Scholar] [CODE]
DCGP-KD [Cheng et al., IEEE TAI 2023] Domain-centroid-guided progressive teacher-based knowledge distillation for source-free domain adaptation of histopathological images [PDF] [G-Scholar]
SCD [Zhou et al., Computers in Biology and Medicine 2023] Superpixel-guided class-level denoising for unsupervised domain adaptive fundus image segmentation without source data [PDF] [G-Scholar]
CP3Net [Feng et al., Knowledge-Based Systems 2023] Cross-platform privacy-preserving CT image COVID-19 diagnosis based on source-free domain adaptation [PDF] [G-Scholar]
CBCOST [Huang et al., Artificial Intelligence in Medicine 2023] Source-free domain adaptive segmentation with class-balanced complementary self-training [PDF] [G-Scholar]
RAF [Yuan et al., The Visual Computer 2023] Data privacy protection domain adaptation by roughing and finishing stage [PDF] [G-Scholar]
... [Wang et al., Health Information Science and Systems 2023] M-MSSEU: Source-free domain adaptation for multi-modal stroke lesion segmentation using shadowed sets and evidential uncertainty [PDF] [G-Scholar]
... [Li et al., IEEE Open Journal of Signal Processing 2023] Source-data-free cross-domain knowledge transfer for semantic segmentation [PDF] [G-Scholar--]
SUP [Xu et al., arXiv 2023] Unsupervised cross-domain pulmonary nodule detection without source data [PDF] [G-Scholar]
MAME [Dong et al., arXiv 2023] Tailored multi-organ segmentation with model adaptation and ensemble [PDF] [G-Scholar]
FVP [Wang et al., arXiv 2023] FVP: Fourier visual prompting for source-free unsupervised domain adaptation of medical image segmentation [PDF] [G-Scholar]
... [Wang et al., arXiv 2023] Black-box source-free domain adaptation via two-stage knowledge distillation [PDF] [G-Scholar]
SL [Chen and Wang, arXiv 2023] SL: Stable learning in source-free domain adaption for medical image segmentation [PDF] [G-Scholar]
SCDA [Fang et al., arXiv 2023] Source-free collaborative domain adaptation via multi-perspective feature enrichment for functional MRI analysis [PDF] [G-Scholar]
LGDA [Ye et al., arXiv 2023] Local-global pseudo-label correction for source-free domain adaptive medical image segmentation [PDF] [G-Scholar]
SFADA [Ran et al., arXiv 2023] Source-free active domain adaptation for diabetic retinopathy grading based on ultra-wide-field fundus image [PDF] [G-Scholar] [CODE]
... [Wang et al., arXiv 2023] Dual-reference source-free active domain adaptation for nasopharyngeal carcinoma tumor segmentation across multiple hospitals [PDF] [G-Scholar] [CODE--]
... [Hu et al., arXiv 2023] A chebyshev confidence guided source-free domain adaptation framework for medical image segmentation [PDF] [G-Scholar]
PD [Rafiee et al., Misc 2023] Diversified source-free domain adaptation [PDF] [G-Scholar--]
... [Pourreza., Master Thesis 2023] Open-set source-free domain adaptation in fundus images analysis [PDF] [G-Scholar--]

2024

SF-UT [Hao et al., Proc. ECCV 2024] Simplifying source-free domain adaptation for object detection: Effective self-training strategies and performance insights [PDF] [G-Scholar] [CODE]
PLPB [Li et al., Proc. WACV 2024] Robust source-free domain adaptation for fundus image segmentation [PDF] [G-Scholar] [CODE]
... [Guichemerre et al., Proc. CVPR Workshops 2024] Source-free domain adaptation of weakly-supervised object localization models for histology [PDF] [G-Scholar] [CODE]
RSA [Zeng et al., Proc. MICCAI 2024] Reliable source approximation: Source-free unsupervised domain adaptation for vestibular schwannoma MRI segmentation [PDF] [G-Scholar] [CODE]
IPLC [Zhang et al., Proc. MICCAI 2024] IPLC: Iterative pseudo label correction guided by SAM for source-free domain adaptation in medical image segmentation [PDF] [G-Scholar] [CODE]
D2SFDA [Zhou et al., Proc. BIBM 2024] Diffusion-driven dual-flow source-free domain adaptation for medical image segmentation [PDF] [G-Scholar--] [CODE--]
A-SFUDA [Zhang et al., Proc. CAI 2024] Asymmetric source-free unsupervised domain adaptation for medical image diagnosis [PDF] [G-Scholar]
... [Nakhaei et al., Proc. SPIE Medical Imaging 2024] Refining boundaries of the segment anything model in medical images using an active contour model [PDF] [G-Scholar]
Distill-SODA [Vray et al., IEEE TMI 2024] Distill-SODA: Distilling self-supervised vision transformer for source-free open-set domain adaptation in computational pathology [PDF] [G-Scholar] [CODE]
MS-MATS [Chen et al., Medical Image Analysis 2024] Cross-center model adaptive tooth segmentation [PDF] [G-Scholar--]
... [Yin et al., Scientific Reports 2024] Source free domain adaptation for kidney and tumor image segmentation with wavelet style mining [PDF] [G-Scholar]
CCMT [Zhang et al., Neurocomputing 2024] Source-free domain adaptation framework based on confidence constrained mean teacher for fundus image segmentation [PDF] [G-Scholar--]
UCDA [Yu and Pei et al., Applied Sciences 2024] Uncertainty-guided asymmetric consistency domain adaptation for histopathological image classification [PDF] [G-Scholar]
... [Liu and Jiao, Biomedical Engineering Letters 2024] Cross-domain additive learning of new knowledge rather than replacement [PDF] [G-Scholar--]
... [Zhang et al., International Journal of Ophthalmology 2024] Diabetic retinopathy identification based on multi-source-free domain adaptation [PDF] [G-Scholar]
VP-SFDA [Chen et al., Health Data Science 2024] VP-SFDA: Visual prompt source-free domain adaptation for cross-modal medical image [PDF] [G-Scholar--]
UniFed [Dinsdale et al., arXiv 2024] UniFed: A unified deep learning framework for segmentation of partially labelled, distributed neuroimaging data [PDF] [G-Scholar]
DyNA [Chen et al., arXiv 2024] Day-night adaptation: An innovative source-free adaptation framework for medical image segmentation [PDF] [G-Scholar]
... [Sun and Rostami, arXiv 2024] Cross-domain distribution alignment for segmentation of private unannotated 3D medical Images [PDF] [G-Scholar]
... [Peralta et al., Misc 2024] Source-free domain adaptation for improving medical image quality in clinical applications [PDF] [G-Scholar--]

2025

AIF-SFDA [Li et al., Proc. AAAI 2025] AIF-SFDA: Autonomous information filter-driven source-free domain adaptation for medical image segmentation [PDF] [G-Scholar] [CODE]
MPPL-SFDA [Zhang et al., Biomedical Signal Processing and Control 2025] Multicentric prototype and pseudo-labeling based source-free domain adaptation for Alzheimer's disease classification [PDF] [G-Scholar--]
C2MAL [Zhou et al., Medical & Biological Engineering & Computing 2025] C2MAL: Cascaded network-guided class-balanced multi-prototype auxiliary learning for source-free domain adaptive medical image segmentation [PDF] [G-Scholar--]

Video Classification

2022

ATCoN [Xu et al., Proc. ECCV 2022] Learning temporal consistency for source-free video domain adaptation [PDF] [G-Scholar] [CODE]
MTRAN [Huang et al., Proc. ACMMM 2022] Relative alignment network for source-free multimodal video domain adaptation [PDF] [G-Scholar]
SFTADA [Chen and Ma, Proc. ICMR 2022] Source-free temporal attentive domain adaptation for video action recognition [PDF] [G-Scholar]
RNA++ [Plananamente et al., Proc. ICIAP 2022] Test-time adaptation for egocentric action recognition [PDF] [G-Scholar] [CODE]
CleanAdapt [Dasgupta et al., Proc. ICVGIP 2022] Overcoming label noise for source-free unsupervised video domain adaptation [PDF] [G-Scholar]

2023

STHC [Li et al., Proc. CVPR 2023] Source-free video domain adaptation with spatial-temporal-historical consistency learning [PDF] [G-Scholar]
DALL-V [Zara et al., Proc. ICCV 2023] The unreasonable effectiveness of large language-vision models for source-free video domain adaptation [PDF] [G-Scholar] [CODE--]
LCMV [Neubert et al., Proc. ICIAP 2023] LCMV: Lightweight classification module for video domain adaptation [PDF] [G-Scholar]
... [Neubert., Master Thesis 2023] Source-free domain adaptation for video action recognition [PDF] [G-Scholar]
CleanAdapt [Dasgupta et al., Misc 2024] Source-free video domain adaptation by learning from noisy labels [PDF] [G-Scholar--] [CODE]
CleanAdapt+TS [Neubert et al., Pattern Recognition 2025] Source-free video domain adaptation by learning from noisy labels [PDF] [G-Scholar--] [CODE]

3D Perception

3D Object Detection

SF-UDA3D [Saltori et al., Proc. 3DV 2020] SF-UDA3D: Source-free unsupervised domain adaptation for lidar-based 3d object detection [PDF] [G-Scholar] [CODE]
ST3D [Yang et al., Proc. CVPR 2021] ST3D: Self-training for unsupervised domain adaptation on 3d object detection [PDF] [G-Scholar] [CODE]
Dreaming [You et al., Proc. ICRA 2022] Exploiting playbacks in unsupervised domain adaptation for 3d object detection [PDF] [G-Scholar]
UAMT [Hegde et al., Proc. ICRA 2023] Source-free unsupervised domain adaptation for 3D object detection in adverse weather [PDF] [G-Scholar] [CODE]

~~ [Hegde et al., arXiv 2021] Uncertainty-aware mean teacher for source-free unsupervised domain adaptive 3d object detection [PDF] [G-Scholar] [CODE]~~
AP-SFDA [Hegde et al., Proc. WACV 2024] Attentive prototypes for source-free unsupervised domain adaptive 3d object detection [PDF] [G-Scholar] [CODE]

3D Pose Estimation

Anat-SFDA [Bigalke et al., arXiv 2022] Anatomy-guided domain adaptation for 3D in-bed human pose estimation [PDF] [G-Scholar] [CODE]

3D Lidar Segmentation

GIPSO [Saltori et al., Proc. ECCV 2022] GIPSO: Geometrically informed propagation for online adaptation in 3d lidar segmentation [PDF] [G-Scholar] [CODE]
LiDAR-UDA [Shaban et al., Proc. ICCV 2023] LiDAR-UDA: Self-ensembling through time for unsupervised LiDAR domain adaptation [PDF] [G-Scholar] [CODE]
TTYD [Michele et al., Proc. ECCV 2024] Train till you drop: Towards stable and robust source-free unsupervised 3D domain adaptation [PDF] [G-Scholar] [CODE]

3D Lidar Recognition

GeoAdapt [Knights et al., IEEE Robotics and Automation Letters 2023] GeoAdapt: Self-supervised test-time adaptation in LiDAR place recognition using geometric priors [PDF] [G-Scholar] [CODE--]

3D Pose Estimation

... [Kaushik et al., Proc. ICLR 2024] Source-free and image-only unsupervised domain adaptation for category level object pose estimation [PDF] [G-Scholar]

Facial Analysis

Face Anti-spoofing

AdaptML [Wang et al., Proc. AAAI 2021] Self-domain adaptation for face anti-spoofing [PDF] [G-Scholar]
Self-Ensemble [Lv et al., Proc. ICASSP 2021] Combining dynamic image and prediction ensemble for cross-domain face anti-spoofing [PDF] [G-Scholar]
GDA [Zhou et al., Proc. ECCV 2022] Generative domain adaptation for face anti-spoofing [PDF] [G-Scholar]
SDA-FAS [Liu et al., Proc. ECCV 2022] Source-free domain adaptation with contrastive domain alignment and self-supervised exploration for face anti-spoofing [PDF] [G-Scholar] [CODE]
SDA-FAS++ [Liu et al., IEEE TPAMI 2024] Source-free domain adaptation with domain generalized pretraining for face anti-spoofing [PDF] [G-Scholar]

Occluded Face Recognition

SFOFR [Zhang et al., Proc. ICASSP 2022] Free lunch for cross-domain occluded face recognition without source data [PDF] [G-Scholar]

Facial Expression Recognition

CluP [Conti et al., Proc. BMVC 2022] Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [PDF] [G-Scholar] [CODE]
LTVAL [Guo et al., Multimedia Tools and Applications 2023] LTVAL: Label transfer virtual adversarial learning framework for source-free facial expression recognition [PDF] [G-Scholar]

Face forgery detection

... [Xu et al., CVIU 2024] Uncertainty guided test-time training for face forgery detection [PDF] [G-Scholar--]

Other CV Applications

Person ReID

MtASD [Wu et al., Proc. CVPR 2019] Distilled person re-identification: Towards a more scalable system [PDF] [G-Scholar]
MSFDA-PT [Ding et al., The Visual Computer 2021] Source-free unsupervised multi-source domain adaptation via proxy task for person re-identification [PDF] [G-Scholar]
... [Song et al., Applied Sciences 2023] Unsupervised vehicle re-identification method based on source-free knowledge transfer [PDF] [G-Scholar]
S2ADAP [Qu et al., Knowledge-Based Systems 2023] Source-free style-diversity adversarial domain adaptation with privacy-preservation for person re-identification [PDF] [G-Scholar]
IAMT [Qu et al., ACM TOMM 2024] Instance-level adversarial source-free domain adaptive person re-identification [PDF] [G-Scholar--]
AAMT [Qu et al., IEEE TMM 2024] AAMT: Adversarial attack-driven mutual teaching for source-free domain-adaptive person reidentification [PDF] [G-Scholar]
SFPS [Yan et al., Pattern Recognition 2025] Source-free domain adaptive person search [PDF] [G-Scholar]

Multi-modality

SOCKET [Ahmed et al., Proc. ECCV 2022] Cross-modal knowledge transfer without task-relevant source data [PDF] [G-Scholar] [CODE]
PopNet [Wu et al., arXiv 2022] Source-free depth for object pop-out [PDF] [G-Scholar] [CODE--]
UPL [Huang et al., arXiv 2022] Unsupervised prompt learning for vision-language models [PDF] [G-Scholar] [CODE]
POUF [Tanwisuth et al., Proc. ICML 2023] POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models [PDF] [G-Scholar] [CODE]
SUMMIT [Simons et al., Proc. ICCV 2023] SUMMIT: Source-free adaptation of uni-modal models to multi-modal targets [PDF] [G-Scholar] [CODE]
MISFIT [Rizzoli et al., arXiv 2023] Source-free domain adaptation for RGB-D semantic segmentation with vision transformers [PDF] [G-Scholar]
CPL [Zhang et al., Proc. ICML 2024] Candidate pseudolabel learning: Enhancing vision-language models by prompt tuning with unlabeled data [PDF] [G-Scholar] [CODE]
FPL/GRIP [Menghini et al., Proc. NeurIPS 2024] Enhancing CLIP with CLIP: Exploring pseudolabeling for limited-label prompt tuning [PDF] [G-Scholar] [CODE]
Frolic [Zhu et al., Proc. NeurIPS 2024] Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting [PDF] [G-Scholar] [CODE--]
EventDance [Zheng and Wang, Proc. CVPR 2024] EventDance: Unsupervised source-free cross-modal adaptation for event-based object recognition [PDF] [G-Scholar]
ZLaP [Stojnić et al., Proc. CVPR 2024] Label propagation for zero-shot classification with vision-language models [PDF] [G-Scholar] [CODE]
uCAP [Nguyen et al., Proc. ECCV 2024] uCAP: An unsupervised prompting method for vision-language models [PDF] [G-Scholar]
NtUA [Ali and Khan, Proc. ECCV 2024] Noise-tolerant few-shot unsupervised adapter for vision-language models [PDF] [G-Scholar]
... [Zhan et al., Proc. IJCAI 2024] Towards dynamic-prompting collaboration for source-free domain adaptation [PDF] [G-Scholar] [CODE]
ReCLIP [Hu et al., Proc. WACV 2024] ReCLIP: Refine contrastive language image pre-training with source free domain adaptation [PDF] [G-Scholar] [CODE]
DIFO [Tang et al., Proc. WACV 2024] Source-free domain adaptation with frozen multimodal foundation model [PDF] [G-Scholar]
OT-VP [Zhang et al., Proc. CVPR Workshops 2024] OT-VP: Optimal transport-guided visual prompting for test-time adaptation [PDF] [G-Scholar--]
QED [Liu et al., IEEE TCSVT 2024] Question type-aware debiasing for test-time visual question answering model adaptation [PDF] [G-Scholar]
BBC [Tian et al., Signal, Image and Video Processing 2024] CLIP-guided black-box domain adaptation of image classification [PDF] [G-Scholar]
TGKT [Zhu et al., arXiv 2024] Source-free cross-modal knowledge transfer by unleashing the potential of task-irrelevant data [PDF] [G-Scholar]
TFUP [Long et al., arXiv 2024] Training-free unsupervised prompt for vision-language models [PDF] [G-Scholar] [CODE]
RCL [Chen et al., arXiv 2024] Empowering source-free domain adaptation with MLLM-driven curriculum learning [PDF] [G-Scholar] [CODE--]
TransCLIP [Zanella et al., arXiv 2024] Boosting vision-language models with transduction [PDF] [G-Scholar] [CODE]
DPA [Ali et al., arXiv 2024] DPA: Dual prototypes alignment for unsupervised adaptation of vision-language models [PDF] [G-Scholar]
EventDance++ [Zheng and Wang, arXiv 2024] EventDance: Unsupervised source-free cross-modal adaptation for event-based object recognition [PDF] [G-Scholar] [CODE--]
LatteCLIP [Cao et al., arXiv 2024] LatteCLIP: Unsupervised CLIP fine-tuning via LMM-synthetic texts [PDF] [G-Scholar]
CDBN [Li et al., arXiv 2024] Data-efficient CLIP-powered dual-branch networks for source-free unsupervised domain adaptation [PDF] [G-Scholar]
LAD [Peng et al., arXiv 2024] Language-guided alignment and distillation for source-free domain adaptation [PDF] [G-Scholar--]
ECALP [Li et al., arXiv 2024] Efficient and context-aware label propagation for zero-/few-shot training-free adaptation of vision-language model [PDF] [G-Scholar]
L2C [Chi et al., Proc. ICLR 2025] Learning to adapt frozen CLIP for few-shot test-time domain adaptation [PDF] [G-Scholar--]
GTA-CLIP [Saha et al., arXiv 2025] Generate, transduct, adapt: Iterative transduction with VLMs [PDF] [G-Scholar] [CODE--]

Image Super-Resolution

SOSR [Ai et al., arXiv 2023] SOSR: Source-free image super-resolution with wavelet augmentation transformer [PDF] [G-Scholar]

Image Dehazing

DRN [Yu et al., Proc. ACMMM 2022] Source-free domain adaptation for real-world image dehazing [PDF] [G-Scholar]

Image Harmonization

Harmonizing-Flows [Beizaee et al., arXiv 2024] Harmonizing flows: Unsupervised MR harmonization based on normalizing flows [PDF] [G-Scholar] [CODE] ~~- Harmonizing-Flows [Beizaee et al., arXiv 2023] Harmonizing flows: Unsupervised MR harmonization based on normalizing flows [PDF] [G-Scholar] [CODE]~~

Video Quality Enhancement

CVQE-MT [Wang, Proc. ICCWAMTIP 2022] An unsupervised domain adaptation method for compressed video quality enhancement [PDF] [G-Scholar]

Image Quality Assessment

SFDA-SSLBN [Liu et al., arXiv 2022] Source-free unsupervised domain adaptation for blind image quality assessment [PDF] [G-Scholar]

Road Segmentation (binary)

SS-SFDA [Kothandaraman et al., Proc. ICCV Workshops 2021] SS-SFDA: Self-supervised source-free domain adaptation for road segmentation in hazardous environments [PDF] [G-Scholar] [CODE]

Sign Segmentation

CMPL [Renz et al., Proc. CVPR Workshops 2021] Sign segmentation with changepoint-modulated pseudo-labelling [PDF] [G-Scholar] [CODE]

Visual Document Understanding

DocTTA [Ebrahimi et al., arXiv 2022] Test-time adaptation for visual document understanding [PDF] [G-Scholar] [DATA]

2D Keypoint Detection (Pose estimation)

MAPS [Ding et al., IEEE TCSVT 2023] MAPS: A noise-robust progressive learning approach for source-free domain adaptive keypoint detection [PDF] [G-Scholar] [CODE]
... [Peng et al., Proc. ICCV 2023] Source-free domain adaptive human pose estimation [PDF] [G-Scholar]
... [Raychaudhuri et al., Proc. ICCV 2023] Prior-guided source-free domain adaptation for human pose estimation [PDF] [G-Scholar]
... [Santoso and Wijaya, Asian American Research Letters Journal 2024] Unsupervised domain adaptation for human pose estimation in the absence of source data [PDF] [G-Scholar]

Tracking

DARTH [Segu et al., Proc. ICCV 2023] DARTH: Holistic test-time adaptation for multiple object tracking [PDF] [G-Scholar] [CODE]
OC-SORT [Shu et al., ITE Technical Report 2024] Exploring source-free domain adaption in multiple object tracking [PDF] [G-Scholar--]

Anomaly detection

CaSA [Bozorgtabar et al., Proc. BMVC 2022] Anomaly detection and localization using attention-guided synthetic anomaly and test-time adaptation [PDF] [G-Scholar]
AnoVL [Deng et al., arXiv 2023] AnoVL: Adapting vision-language models for unified zero-shot anomaly localization [PDF] [G-Scholar]
... [Klüttermann and Müller, arXiv 2024] About test-time training for outlier detection [PDF] [G-Scholar] [CODE]

Retrieval

T3AR [Zancato et al., Proc. CVPR 2023] Train/test-time adaptation with retrieval [PDF] [G-Scholar]
DISC [Ma et al., IEEE TMM 2024] Discrepancy and structure-based contrast for test-time adaptive retrieval [PDF] [G-Scholar]
PCLO [Li et al., IEEE TCSVT 2024] Progressive contrastive label optimization for source-free universal 3D model retrieval [PDF] [G-Scholar--]

Gaze estimation

UnReGA [Cai et al., Proc. CVPR 2023] Source-free adaptive gaze estimation by uncertainty reduction [PDF] [G-Scholar] [CODE--]

Hand-Object Interaction

POV [Xu et al., Proc. ACMMM 2023] POV: Prompt-oriented view-agnostic learning for egocentric hand-object interaction in the multi-view world [PDF] [G-Scholar]

Human Activity Recognition

SF-Adapter [Kang et al., Proc. IMWUT 2023] SF-Adapter: Computational-efficient source-free domain adaptation for human activity recognition [PDF] [G-Scholar]

Handwritten Text Recognition

AMD [Alfaro-Contreras and Calvo-Zaragoza, arXiv 2024] Align, minimize and diversify: A source-free unsupervised domain adaptation method for handwritten text recognition [PDF] [G-Scholar]

Misc

... [Rufin et al., arXiv 2023] Taking it further: Leveraging pseudo labels for field delineation across label-scarce smallholder regions [PDF] [G-Scholar]
... [Mohammadi et al., Remote Sensing of Environment 2024] A source-free unsupervised domain adaptation method for cross-regional and cross-time crop mapping from satellite image time series [PDF] [G-Scholar] [CODE]
SFDA-rPPG [Xie et al., arXiv 2024] SFDA-rPPG: Source-free domain adaptive remote physiological measurement with spatio-temporal consistency [PDF] [G-Scholar] [CODE]
... [Wen et al., arXiv 2024] Generalizing segmentation foundation model under sim-to-real domain-shift for guidewire segmentation in X-ray fluoroscopy [PDF] [G-Scholar--]

Beyond CV Applications

2020

... [Laparra et al., JAMIA open 2020] Rethinking domain adaptation for machine learning over clinical language [PDF] [G-Scholar]

2021

CdKD [Zhao et al., Proc. ACL 2021] Matching distributions between model and data: Cross-domain knowledge distillation for unsupervised domain adaptation [PDF] [G-Scholar]
PPT [Kurniawan et al., Proc. EACL 2021] PPT: Parsimonious parser transfer for unsupervised cross-lingual adaptation [PDF] [G-Scholar] [CODE]
... [Kedia et al., Proc. ECAL 2021] Keep learning: Self-supervised meta-learning for learning from inference [PDF] [G-Scholar]
ActiveST [Su et al., Proc. ACL SemEval 2021] The University of Arizona at SemEval-2021 task 10: Applying self-training, active learning and data augmentation to source-free domain adaptation [PDF] [G-Scholar]
... [Laparra et al., Proc. ACL SemEval 2021] SemEval-2021 task 10: Source-free domain adaptation for semantic processing [PDF] [G-Scholar]
e-SHOT-CE [Cao et al., IEEE TVT 2021] Towards cross-environment human activity recognition based on radar without source data [PDF] [G-Scholar]

2022

... [Su et al., Proc. ACL 2022] A comparison of strategies for source-free domain adaptation [PDF] [G-Scholar] [CODE]
... [Kurniawan et al., Proc. NAACL 2022] Unsupervised cross-lingual transfer of structured predictors without source data [PDF] [G-Scholar] [CODE]
IDANI [Antverg et al., Proc. ACL Workshops 2022] IDANI: Inference-time domain adaptation via neuron-level interventions [PDF] [G-Scholar] [CODE]
... [Zhang et al., Proc. China Automation Congress 2022] Source-free domain adaptation for rotating machinery cross-domain fault diagnosis with neighborhood reciprocity clustering [PDF] [G-Scholar--]
... [Zhu et al., Proc. ICSMD 2022] Source-free unsupervised domain adaptation for privacy-preserving intelligent fault diagnosis [PDF] [G-Scholar]
MDMAML [Li et al., IEEE CIM 2022] Meta-learning for fast and privacy-preserving source knowledge transfer of EEG-based BCIs [PDF] [G-Scholar]
MSDT [Zhang et al., IEEE TNSRE 2022] Multi-source decentralized transfer for privacy-preserving BCIs [PDF] [G-Scholar]
LSFT [Zhang and Wu, IEEE TCDS 2022] Lightweight source-free transfer for privacy-preserving motor imagery classification [PDF] [G-Scholar]
ASFA [Xia et al., IEEE TBE 2022] Privacy-preserving domain adaptation for motor imagery-based brain-computer interfaces [PDF] [G-Scholar] [CODE]
T-ISTGNN [Qi et al., IEEE TITS 2022] Privacy-preserving cross-area traffic forecasting in ITS: A transferable spatial-temporal graph neural network approach [PDF] [G-Scholar]
DP-SFDA [An et al., IEEE TITS 2022] A privacy-preserving unsupervised domain adaptation framework for clinical text analysis [PDF] [G-Scholar]
SFAD [Jiao et al., IEEE TII 2022] Source-free adaptation diagnosis for rotating machinery [PDF] [G-Scholar]
scEMAIL [Wan et al., Genomics, Proteomics and Bioinformatics 2022] scEMAIL: Universal and source-free annotation method for scRNA-seq data with novel cell-type perception [PDF] [G-Scholar] [CODE]
... [Wang et al., Chinese Journal of Aeronautics 2022] Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis [PDF] [G-Scholar]
MDAQA [Yin et al., arXiv 2022] Source-free domain adaptation for question answering with masked self-training [PDF] [G-Scholar]

2023

NOTELA [Boudiaf et al., Proc. ICML 2023] In search for a generalizable method for source free domain adaptation [PDF] [G-Scholar]

~~[Boudiaf et al., Misc 2023] NOTELA: A generalizable method for source free domain adaptation [PDF]~~
TaU [Zhan et al., Proc. ACL 2023] Test-time adaptation for machine translation evaluation by uncertainty minimization [PDF] [G-Scholar] [CODE--]
FLOOD [Liu et al., Proc. KDD 2023] FLOOD: A flexible invariant learning framework for out-of-distribution generalization on graphs [PDF] [G-Scholar]
MAPU [Ragab et al., Proc. KDD 2023] Source-free domain adaptation with temporal imputation for time series data [PDF] [G-Scholar] [CODE]
TALC [Wei et al., Proc. EMNLP Findings 2023] Leveraging multiple teachers for test-time adaptation of language-guided classifiers [PDF] [G-Scholar--] [CODE--]
... [Lee et al., Proc. BCI 2023] Source-free cross-domain state of charge estimation of lithium-ion batteries at different ambient temperatures [PDF] [G-Scholar] [CODE]
SFQA [Zhao et al., Proc. ICASSP 2023] Source-free unsupervised domain adaptation for question answering [PDF] [G-Scholar]
BKD-SFUDA [Tian et al., Proc. CSCWD 2023] Knowledge distillation with source-free unsupervised domain adaptation for BERT model compression [PDF] [G-Scholar--]
... [Wang et al., Proc. IEEE ICMA 2023] Source-free domain adaptation network for rolling bearing fault diagnosis [PDF] [G-Scholar--]
DSP [Liu et al., Proc. AIMLR 2023] Adaptive speech recognition via dual-level sequential pseudo labels [PDF] [G-Scholar--]
... [Zhang et al., Proc. ASRU 2023] Consistency based unsupervised self-training for ASR personalisation [PDF] [G-Scholar--]
... [Islam et al., Proc. ETFG 2023] Location agnostic source-free domain adaptive learning to predict solar power generation [PDF] [G-Scholar]
SFTTN [Shen et al., IEEE TPEL 2023] Source-free cross-domain state of charge estimation of lithium-ion batteries at different ambient temperatures [PDF] [G-Scholar]
... [Yue et al., IEEE TIM 2023] Multiple source-free domain adaptation network based on knowledge distillation for machinery fault diagnosis [PDF] [G-Scholar]
... [Wu et al., IEEE TIM 2023] Privacy-preserving adaptive remaining useful life prediction via source free domain adaption [PDF] [G-Scholar] [CODE]
SF-CA [Zhu et al., IEEE TIM 2023] Source-free cluster adaptation for privacy-preserving machinery fault diagnosis [PDF] [G-Scholar]
... [Zhu et al., IEEE TIM 2023] Dual contrastive training and transferability aware adaptation for multi-source privacy-preserving motor imagery classification [PDF] [G-Scholar] [CODE]
... [Zhao et al., IEEE TII 2023] Source-free domain adaptation for privacy-preserving seizure prediction [PDF] [G-Scholar]
TASFA [Xiao et al., IEEE TII 2023] Temporal attention source-free adaptation for chemical processes fault diagnosis [PDF] [G-Scholar--]
B2TSDA [Ren et al., IEEE TCYB 2023] Single/multi-source black-box domain adaption for sensor time series data [PDF] [G-Scholar]
SS-TrBoosting [Zhao et al., IEEE TNSRE 2023] Source-free domain adaptation (SFDA) for privacy-preserving seizure subtype classification [PDF] [G-Scholar]
... [Wang et al., IEEE Internet of Things Journal 2023] Wireless IoT monitoring system in Hong Kong–Zhuhai–Macao bridge and edge computing for anomaly detection [PDF] [G-Scholar]
... [Dridi et al., Building and Environment 2023] Unsupervised domain adaptation with and without access to source data for estimating occupancy and recognizing activities in smart buildings [PDF] [G-Scholar]
... [Dridi et al., Energy and Buildings 2023] Unsupervised domain adaptation without source data for estimating occupancy and recognizing activities in smart buildings [PDF] [G-Scholar]
SFDAF [Li et al., Reliability Engineering and System Safety 2023] Source-free domain adaptation framework for fault diagnosis of rotation machinery under data privacy [PDF] [G-Scholar]
UCSN [Li et al., IEEE Sensors Journal 2023] Unsupervised continual source-free network for fault diagnosis of machines under multiple diagnostic domains [PDF] [G-Scholar]
PPDA [Wang et al., IEEE Sensors Journal 2023] Privacy-preserving domain adaptation for intracranial EEG classification via information maximization and gaussian mixture model [PDF] [G-Scholar]
HSSC-EMM [Zhang et al., Mechanical Systems and Signal Processing 2023] Universal source-free domain adaptation method for cross-domain fault diagnosis of machines [PDF] [G-Scholar]
... [Li et al., Journal of Manufacturing Systems 2023] Federated transfer learning in fault diagnosis under data privacy with target self-adaptation [PDF] [G-Scholar]
TAPDA [Yuan and Siyal, Biomedical Signal Processing and Control 2023] Target-oriented augmentation privacy-protection domain adaptation for imbalanced ECG beat classification [PDF] [G-Scholar]
... [Zhao et al., Measurement Science and Technology 2023] Single-source UDA for privacy-preserving intelligent fault diagnosis based on domain augmentation [PDF] [G-Scholar]
MWSDTN [Gao et al., Expert Systems With Applications 2023] Multi-source weighted source-free domain transfer method for rotating machinery fault diagnosis [PDF] [G-Scholar]
... [Tian et al., Reliability Engineering & System Safety 2023] A novel generalized source-free domain adaptation approach for cross-domain industrial fault diagnosis [PDF] [G-Scholar]
... [Guney et al., arXiv 2023] Source free domain adaptation of a DNN for SSVEP-based brain-computer interfaces [PDF] [G-Scholar--] [CODE--]
AMFDA [Salimnia., Master Thesis 2023] Attention-based multi-source-free domain adaptation for EEG emotion recognition [PDF] [G-Scholar]
... [Niknam., Master Thesis 2023] Source-free domain adaptation for sleep stage classification [PDF] [G-Scholar]

2024

... [Vermani et al., Proc. ICLR 2024] Leveraging generative models for unsupervised alignment of neural time series data [PDF] [G-Scholar]
RNA [Luo et al., Proc. IJCAI 2024] Rank and align: Towards effective source-free graph domain adaptation [PDF] [G-Scholar]
GraphCTA [Zhang et al., Proc. WWW 2024] Collaborate to adapt: Source-free graph domain adaptation via bi-directional adaptation [PDF] [G-Scholar] [CODE]
SOGA [Mao et al., Proc. WSDM 2024] Source free graph unsupervised domain adaptation [PDF] [G-Scholar]

~~[Mao et al., arxiv 2024] Source free unsupervised graph domain adaptation [PDF] [G-Scholar]~~
... [Flynn and Ragni, Proc. Interspeech 2024] Self-train before you transcribe [PDF] [G-Scholar--]
CHDA [Chien et al., Proc. Interspeech 2024] Collaborative contrastive learning for hypothesis domain adaptation [PDF] [G-Scholar]
CaHTN [Wang et al., Proc. Interspeech 2024] Confidence-aware hypothesis transfer networks for source-free cross-corpus speech emotion recognition [PDF] [G-Scholar]
... [Oiso et al., Proc. Interspeech 2024] Prompt tuning for audio deepfake detection: Computationally efficient test-time domain adaptation with limited target dataset [PDF] [G-Scholar]
PASAL [Yin et al., Proc. NAACL Findings 2024] Source-free unsupervised domain adaptation for question answering via prompt-assisted self-learning [PDF] [G-Scholar]
SFPS [Shimizu, et al., Proc. ACL Findings 2024] Improving self-training with prototypical learning for source-free domain adaptation on clinical text [PDF] [G-Scholar]
SF-ABSA [Zhao et al., Proc. LREC-COLING 2024] Source-free domain adaptation for aspect-based sentiment analysis [PDF] [G-Scholar]
... [Bu et al., Proc. KSEM 2024] Weighted multiple source-free domain adaptation ensemble network in intelligent machinery fault diagnosis [PDF] [G-Scholar]
ECAN [Zhao et al., Proc. ICASSP 2024] Emotion-aware contrastive adaptation network for source-free cross-corpus speech emotion recognition [PDF] [G-Scholar]
... [Liu et al., Proc. ICASSP 2024] Source-free domain adaptation for millimeter wave radar based human activity recognition [PDF] [G-Scholar]
PAW [Huang et al., Proc. ICASSP 2024] Privacy-preserving attention-weighted multi-source domain adaptation for EEG motor imagery [PDF] [G-Scholar]
SFDA-OMR [Roselló et al., Proc. ICDAR 2024] Source-free domain adaptation for optical music recognition [PDF] [G-Scholar] [CODE]
... [Wang et al., Proc. I2MTC 2024] A clustering-guided source-free domain transfer learning diagnostic method for rotating machiner [PDF] [G-Scholar--]
SODAN [Yue et al., Proc. I2MTC 2024] Source-free open-set domain adaptation network for emerging fault diagnosis of planetary gearbox [PDF] [G-Scholar--]
GALA [Luo et al., IEEE TPAMI 2024] GALA: Graph diffusion-based alignment with Jigsaw for source-free domain adaptation [PDF] [G-Scholar] [CODE]
ISFAD [Liu et al., IEEE TIM 2024] Imbalanced source-free adaptation diagnosis for rotating machinery [PDF] [G-Scholar]
SF-UDA [Kumar et al., IEEE TIM 2024] Mitigating negative transfer learning in source free-unsupervised domain adaptation for rotating machinery fault diagnosis [PDF] [G-Scholar]
... [Zhong et al., IEEE TIM 2024] Source-free domain adaptation with self-supervised learning for non-intrusive load monitoring [PDF] [G-Scholar]
SPARK [Yuan et al., IEEE JBHI 2024] SPARK: a high-efficiency black-box domain adaptation framework for source privacy-preserving drowsiness detection [PDF] [G-Scholar]
AEA [Wang et al., IEEE JBHI 2024] Lightweight source-free domain adaptation based on adaptive euclidean alignment for brain-computer interfaces [PDF] [G-Scholar]
TSSFDA [Jia et al., IEEE TETCI 2024] A two-stage privacy-preserving domain adaptation for industrial time-series prediction [PDF] [G-Scholar--]
... [Chen et al., IEEE Internet of Things Journal 2024] Uncertainty estimation pseudo-labels guided source-free domain adaptation for cross-domain remaining useful life prediction in IIoT [PDF] [G-Scholar--]
EMDKFA [Lin et al., IEEE Internet of Things Journal 2024] Towards efficient multi-domain knowledge fusion adaptation via low-rank reparameterization and noisy label learning: Application to source-free cross-comain fault diagnosis in IIoT [PDF] [G-Scholar--]
... [Hu et al., IEEE Sensors Journal 2024] Fast online fault diagnosis for PMSM based on adaptation model [PDF] [G-Scholar]
... [Zhang et al., IEEE Sensors Journal 2024] Reliable source-free domain adaptation for cross-user myoelectric pattern recognition [PDF] [G-Scholar]
... [Ma et al., Knowledge-Based Systems 2024] Source-free cross-domain fault diagnosis of rotating machinery using the siamese framework [PDF] [G-Scholar]
SFRDA-PLUE [Liu et al., Knowledge-Based Systems 2024] A source free robust domain adaptation approach with pseudo-labels uncertainty estimation for rolling bearing fault diagnosis under limited sample conditions [PDF] [G-Scholar]
AFSF-FD [Li et al., Knowledge-Based Systems 2024] Anti-forgetting source-free domain adaptation method for machine fault diagnosis [PDF] [G-Scholar]
... [Cao et al., Reliability Engineering & System Safety 2024] Source-free domain adaptation for transferable remaining useful life prediction of machine considering source data absence [PDF] [G-Scholar]
... [Yu et al., Reliability Engineering & System Safety 2024] Source-free domain adaptation method for fault diagnosis of rotation machinery under partial information [PDF] [G-Scholar]
SSFDA-DLP [Su et al., Reliability Engineering & System Safety 2024] Semi-supervised source-free domain adaptation method via diffusive label propagation for rotating machinery fault diagnosis [PDF] [G-Scholar]
ACPDA [Li et al., Reliability Engineering & System Safety 2024] Adaptive centroid prototype-based domain adaptation for fault diagnosis of rotating machinery without source data [PDF] [G-Scholar]
... [Lin et al., Reliability Engineering & System Safety 2024] A robust source-free unsupervised domain adaptation method based on uncertainty measure and adaptive calibration for rotating machinery fault diagnosis [PDF] [G-Scholar]
TFFM [Gao et al., Information Fusion 2024] Time- and frequency-domain fusion for source-free adaptation fault diagnosis [PDF] [G-Scholar--]
... [Liu et al., Expert Systems with Applications 2024] Reinforced fuzzy domain adaptation: Revolutionizing data-unaccessible rotating machinery fault diagnosis across multiple domains [PDF] [G-Scholar]
SFDA-CD [Wang and Wu, Remote Sensing 2024] SFDA-CD: A source-free unsupervised domain adaptation for VHR image change detection [PDF] [G-Scholar]
... [Wang et al., Advanced Engineering Informatics 2024] SFDA-T: A novel source-free domain adaptation method with strong generalization ability for fault diagnosis [PDF] [G-Scholar]
... [Wu et al., Acta Energiae Solaris Sinica 2024] Multi-source domain adaptive fault diagnosis method of wind turbine gearbox under no-accessing source data [PDF] [G-Scholar]
... [Mellot et al., arXiv 2024] Physics-informed and unsupervised riemannian domain adaptation for machine learning on heterogeneous EEG datasets [PDF] [G-Scholar]
STAR [Hu et al., arXiv 2024] Self-taught recognizer: Toward unsupervised adaptation for speech foundation models [PDF] [G-Scholar] [CODE]
SSFDA [Guo et al., arXiv 2024] SpGesture: Source-free domain-adaptive sEMG-based gesture recognition with jaccard attentive spiking neural network [PDF] [G-Scholar]
E-MAPU [Gong et al., arXiv 2024] Evidentially calibrated source-free time-series domain adaptation with temporal imputation [PDF] [G-Scholar]
... [Elia et al., arXiv 2024] Source-free domain adaptation for speaker verification in data-scarce languages and noisy channels [PDF] [G-Scholar--]
TAAD [Sun et al., arXiv 2024] Continuous test-time domain adaptation for efficient fault detection under evolving operating conditions [PDF] [G-Scholar]
DT3OR [Yang et al., arXiv 2024] Dual test-time training for out-of-distribution recommender system [PDF] [G-Scholar]
STMA [Gnassounou et al., arXiv 2024] Multi-source and test-time domain adaptation on multivariate signals using spatio-temporal monge alignment [PDF] [G-Scholar]
... [Soylu et al., arXiv 2024] The art of the steal: Purloining deep learning models developed for an ultrasound scanner to a competitor machine [PDF] [G-Scholar]
EverAdapt [Ragab et al., arXiv 2024] EverAdapt: Continuous adaptation for dynamic machine fault diagnosis environments [PDF] [G-Scholar] [CODE]
TemSR [Wang et al., arXiv 2024] Temporal source recovery for time-series source-free unsupervised domain adaptation [PDF] [G-Scholar] [CODE]
SFT [Patel et al., arXiv 2024] Efficient source-free time-series adaptation via parameter subspace disentanglement [PDF] [G-Scholar]
AdaRC [Bao et al., arXiv 2024] AdaRC: Mitigating graph structure shifts during test-time [PDF] [G-Scholar]
SPDIM [Li et al., arXiv 2024] SPDIM: Source-free unsupervised conditional and label shift adaptation in EEG [PDF] [G-Scholar]
GraphATA [Zhang and He, Proc. WWW 2025] Aggregate to adapt: Node-centric aggregation for multi-source-free graph domain adaptation [PDF] [G-Scholar--] [CODE]
KTDA [Jiao et al., IEEE TII 2025] Source-free black-box adaptation for machine fault diagnosis [PDF] [G-Scholar--]
BRR [Zhan et al., Neural Networks 2025] Reducing bias in source-free unsupervised domain adaptation for regression [PDF] [G-Scholar]
TFDA [Furqon et al., Information Sciences 2025] Time and frequency synergy for source-free time-series domain adaptations [PDF] [G-Scholar] [CODE]
CSSL [Wang et al., User Modeling and User-Adapted Interaction 2025] A contrastive self-supervised learning method for source-free EEG emotion recognition [PDF] [G-Scholar]
NUD [Wang et al., Biomedical Signal Processing and Control 2025] Active source-free domain adaptation for intracranial EEG classification via neighborhood uncertainty and diversity [PDF] [G-Scholar--]

Misc

[Yang et al., Proc. ACM-MM2007] Cross-domain video concept detection using adaptive svms [PDF] [G-Scholar]
[Aytal and Zisserman, Proc. ICCV 2011] Tabula rasa: Model transfer for object category detection [PDF] [G-Scholar]
[Kuzborskij et al., Proc. ICML 2013] Stability and hypothesis transfer learning [PDF] [G-Scholar]
[Tommasi et al., IEEE TPAMI 2013] Learning categories from few examples with multi model knowledge transfer [PDF] [G-Scholar]
AdaBN [Li et al., Proc. ICLR 2017] Revisiting batch normalization for practical domain adaptation [PDF] [G-Scholar]
... [Burns and Steinhardt, Proc. CVPR 2021] Limitations of post-hoc feature alignment for robustness [PDF] [G-Scholar] [CODE]
DARE [Rosenfeld et al., Proc. NeurIPS Workshops 2022] Domain-adjusted regression or: ERM may already learn features sufficient for out-of-distribution generalization [PDF] [G-Scholar]
GDSDA [Ao et al., Proc. AAAI 2017] Fast generalized distillation for semi-supervised domain adaptation [PDF] [G-Scholar]
MapNet+ [Brahmbhatt et al., Proc. CVPR 2018] Geometry-aware learning of maps for camera localization [PDF] [G-Scholar]
dkdHTL [Yu et al., arXiv 2020] Dynamic knowledge distillation for black-box hypothesis transfer learning [PDF] [G-Scholar]
TOHAN [Chi et al., Proc. NeurIPS 2021] TOHAN: A one-step approach towards few-shot hypothesis adaptation [PDF] [G-Scholar] [CODE]
LCCS [Zhang et al., Proc. IJCAI 2022] Few-shot adaptation of pre-trained networks for domain shift [PDF] [G-Scholar] [CODE]
CIDA [Kundu et al., Proc. ECCV 2020] Class-incremental domain adaptation [PDF] [G-Scholar]

2023

DEG-Net [Dong et al., Proc. ICML 2023] Diversity-enhancing generative network for few-shot hypothesis adaptation [PDF][G-Scholar]
RMT [Döbler et al., Proc. CVPR 2023] Class-incremental domain adaptation [PDF] [G-Scholar] [CODE]
PromptStyler [Cho et al., Proc. ICCV 2023] PromptStyler: Prompt-driven style generation for source-free domain generalization [PDF] [G-Scholar] [CODE]
SF-DAP [Lee et al., Proc. ICCV 2023] Unsupervised accuracy estimation of deep visual models using domain-adaptive adversarial perturbation without source samples [PDF] [G-Scholar]
... [Ericsson et al., Proc. AutoML 2023] Better practices for domain adaptation [PDF] [G-Scholar]

CIFA [Qi et al., IEEE Signal Processing Letters 2023] Causal intervention for few-shot hypothesis adaptation [PDF] [G-Scholar--]
TIDo [Ambastha and Yun, arXiv 2023] TIDo: Source-free task incremental learning in non-stationary environments [PDF] [G-Scholar]
ALeN [Ambastha and Yun, arXiv 2023] Adversarial learning networks: Source-free unsupervised domain incremental learning [PDF] [G-Scholar]
... [Singh and Diggavi, arXiv 2023] Representation transfer learning via multiple pre-trained models for linear regression [PDF] [G-Scholar]
... [Huang et al., arXiv 2023] Prompt ensemble self-training for open-vocabulary domain adaptation [PDF] [G-Scholar]
PseudoCal [Hu et al., arXiv 2023] PseudoCal: A source-free approach to unsupervised uncertainty calibration in domain adaptation [PDF] [G-Scholar]

2024

MAP [Peng et al., Proc. CVPR 2024] MAP: MAsk-pruning for source-free model intellectual property protection [PDF] [G-Scholar] [CODE--]
TASFAR [He et al., Porc. ICDE 2024] Target-agnostic source-free domain adaptation for regression tasks [PDF] [G-Scholar] [CODE]
... [Leroux et al., Proc. CVPR Workshops 2024] Test-time specialization of dynamic neural networks [PDF] [G-Scholar--]
IM-DCL [Xu et al., IEEE TIP 2024] Enhancing information maximization with distance-aware contrastive learning for source-free cross-domain few-shot learning [PDF] [G-Scholar] [CODE]
TEA [Jin et al., IEEE TMM 2024] Federated hallucination translation and source-free regularization adaptation in decentralized domain adaptation for foggy scene understanding [PDF] [G-Scholar--]
OSFTL [Wu et al., IEEE TNSRE 2024] Online privacy-preserving EEG classification by source-free transfer learning [PDF] [G-Scholar]
CamoNet [Zhang et al., IEEE TMC 2024] CamoNet: On-device neural network adaptation with zero interaction and unlabeled data for diverse edge environments [PDF] [G-Scholar]
RobustDA [Guo et al., IEEE Journal on Emerging and Selected Topics in Circuits and Systems 2024] RobustDA: Lightweight robust domain adaptation for evolving data at edge [PDF] [G-Scholar]
TETOT [Mehra et al., arXiv 2024] Test-time assessment of a model's performance on unseen domains via optimal transport [PDF] [G-Scholar]
L^3 [Xie et al., arXiv 2024] Look, learn and leverage (L^3): Mitigating visual-domain shift and discovering intrinsic relations via symbolic alignment [PDF] [G-Scholar]
... [Zeng et al., arXiv 2024] LLM embeddings improve test-time adaptation to tabular Y|X-shifts [PDF] [G-Scholar] [CODE]
ACT [anonymous et al., Misc 2025] Asymmetric co-training for source-free few-shot domain adaptation [PDF--] [G-Scholar--] [CODE]

Files

TTA-SFDA.md

Latest commit

History

TTA-SFDA.md

File metadata and controls

Awesome Source-Free Domain Adaptation

Contents

Shallow Methods

Image Classification

2020

2021

2022

2023

2024

2025

Attacks and Defenses

Semantic Segmentation

2021

2022

2023

2024

Object Detection

before 2020

2021

2022

2023

2024

Medical Image Analysis

2020

2021

2022

2023

2024

2025

Video Classification

2022

2023

3D Perception

3D Object Detection

3D Pose Estimation

3D Lidar Segmentation

3D Lidar Recognition

3D Pose Estimation

Facial Analysis

Face Anti-spoofing

Occluded Face Recognition

Facial Expression Recognition

Face forgery detection

Other CV Applications

Person ReID

Multi-modality

Image Super-Resolution

Image Dehazing

Image Harmonization

Video Quality Enhancement

Image Quality Assessment

Road Segmentation (binary)

Sign Segmentation

Visual Document Understanding

2D Keypoint Detection (Pose estimation)

Tracking

Anomaly detection

Retrieval

Gaze estimation

Hand-Object Interaction

Human Activity Recognition

Handwritten Text Recognition

Misc

Beyond CV Applications

2020

2021

2022

2023

2024

Misc

2023

2024