Unsupervised Robust Domain Adaptation without Source Data
This addresses the challenge of making models robust and accurate in unsupervised domain adaptation without source data, which is incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of robust domain adaptation when source data and target labels are unavailable, focusing on adversarial robustness, and achieves over 10% accuracy improvement on clean and adversarial samples across four benchmark datasets.
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.