CDA: Contrastive-adversarial Domain Adaptation
This work addresses domain adaptation for machine learning models by improving classification accuracy when source and target domains have different class distributions, though it is incremental as it builds on existing adversarial methods.
The paper tackled the problem of class shift in domain adaptation by proposing a two-stage model called CDA, which combines adversarial learning for domain alignment with contrastive learning for intra-class compactness, achieving state-of-the-art results on Office-31 and Digits-5 datasets.
Recent advances in domain adaptation 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 are significantly different 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 domain adaptation called \textbf{C}ontrastive-adversarial \textbf{D}omain \textbf{A}daptation \textbf{(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, \textit{Office-31} and \textit{Digits-5}, and demonstrate that CDA achieves state-of-the-art results on both datasets.