2022-11-28-fatras22a.md

title	abstract	video	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Optimal Transport meets Noisy Label Robust Loss and MixUp Regularization for Domain Adaptation	It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions. In domain adaptation (DA), one wants to classify unlabeled target images using source labeled images. Unfortunately, deep neural networks trained on a source training set perform poorly on target images which do not belong to the training domain. One strategy to improve these performances is to align the source and target image distributions in an embedded space using optimal transport (OT). To compute OT, most methods use the minibatch optimal transport approximation which causes negative transfer, i.e. aligning samples with different labels, and leads to overfitting. In this work, we mitigate negative alignment by explaining it as a noisy label assignment to target images. We then mitigate its effect by appropriate regularization. We propose to couple the MixUp regularization with a loss that is robust to noisy labels in order to improve domain adaptation performance. We show in an extensive ablation study that a combination of the two techniques is critical to achieve improved performance. Finally, we evaluate our method, called mixunbot, on several benchmarks and real-world DA problems.	https://youtu.be/c_9ozkPdxqw	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	fatras22a	0	Optimal Transport meets Noisy Label Robust Loss and MixUp Regularization for Domain Adaptation	966	981	966-981	966	false	Fatras, Kilian and Naganuma, Hiroki and Mitliagkas, Ioannis	given family Kilian Fatras given family Hiroki Naganuma given family Ioannis Mitliagkas	2022-11-28		Proceedings of The 1st Conference on Lifelong Learning Agents	199	inproceedings	date-parts 2022 11 28	https://proceedings.mlr.press/v199/fatras22a/fatras22a.pdf