Unsupervised Robust Domain Adaptation Without Source Data

Peshal Agarwal, Danda Pani Paudel, Jan-Nico Zaech, Luc Van Gool; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 2009-2018

Abstract


We study the problem of robust domain adaptation in the context of unavailable target labels and source data. The considered robustness is against adversarial perturbations. This paper aims at answering the question of finding the right strategy to make the target model robust and accurate in the setting of unsupervised domain adaptation without source data. The major findings of this paper are: (i) robust source models can be transferred robustly to the target; (ii) robust domain adaptation can greatly benefit from non-robust pseudo-labels and the pair-wise contrastive loss. The proposed method of using non-robust pseudo-labels performs surprisingly well on both clean and adversarial samples, for the task of image classification. We show a consistent performance improvement of over 10% in accuracy against the tested baselines on four benchmark datasets.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Agarwal_2022_WACV, author = {Agarwal, Peshal and Paudel, Danda Pani and Zaech, Jan-Nico and Van Gool, Luc}, title = {Unsupervised Robust Domain Adaptation Without Source Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {2009-2018} }