CDA: Contrastive-adversarial Domain Adaptation
Abstract: Recent advances in unsupervised domain adaptation (UDA) reveal that adversarial learning on deep neural networks can learn domain invariant features to reduce the shift between source and target domains. While such adversarial approaches achieve domain-level alignment, they ignore the class (label) shift. When class-conditional data distributions significantly differ between the source and target domain, it can generate ambiguous features near class boundaries that are more likely to be misclassified. In this work, we propose a two-stage model for UDA called Contrastive-adversarial Domain Adaptation (CDA). While the adversarial component facilitates domain-level alignment, two-stage contrastive learning exploits class information to achieve higher intra-class compactness across domains resulting in well-separated decision boundaries. Furthermore, the proposed contrastive framework is designed as a plug-and-play module that can be easily embedded with existing adversarial methods for domain adaptation. We conduct experiments on two widely used benchmark datasets for domain adaptation, namely, Office-31 and Digits-5, and demonstrate that CDA achieves state-of-the-art results on both datasets.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Jia-Bin_Huang1
Submission Number: 656
Loading