An Incremental Learning, Continual Learning, and Life-Long Learning Repository

A collection of online continual learning paper implementations and tricks for computer vision in PyTorch, including our ASER(AAAI-21), SCR(CVPR21-W) and an online continual learning survey (Neurocomputing).

PyContinual (An Easy and Extendible Framework for Continual Learning)

An Extensible Continual Learning Framework Focused on Language Models (LMs)

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. TPAMI, 2024.

Class-Incremental Learning: A Survey (TPAMI 2024)

Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need (IJCV 2024)

Forward Compatible Few-Shot Class-Incremental Learning (CVPR'22)

Towards increasing stability of neural networks for continual learning: https://arxiv.org/abs/2006.06958.pdf (NeurIPS'20)

Code for the paper "Incremental Learning Techniques for Semantic Segmentation", Michieli U. and Zanuttigh P., ICCVW, 2019

Implementation of "Episodic Memory in Lifelong Language Learning"(NeurIPS 2019) in Pytorch

A PyTorch implementation of the ECCV 2018 publication "Memory Aware Synapses: Learning what (not) to forget"

Pre-training and Lifelong learning for User Embedding and Recommender System

[EMNLP 2022] Continual Training of Language Models for Few-Shot Learning

The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.

[IROS2022] Official repository of InCloud: Incremental Learning for Point Cloud Place Recognition, Published in IROS2022 https://arxiv.org/abs/2203.00807

The code repository for "A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning" (ICLR'23) in PyTorch

Repository of continual learning papers

CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for task-aware parameter-efficient fine-tuning(NeurIPS 2024)

A PyTorch implementation of the CVPR 2017 publication "Expert Gate: Lifelong Learning with a Network of Experts"