Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation
This addresses domain adaptation without source data, improving privacy, but is incremental as it builds on existing contrastive learning methods.
The paper tackles source-free domain adaptation by learning domain-invariant features through contrastive learning and clustering, achieving superior results on benchmarks like VisDA, Office-Home, and Office-31.
Unsupervised domain adaptation uses source data from different distributions to solve the problem of classifying data from unlabeled target domains. However, conventional methods require access to source data, which often raise concerns about data privacy. In this paper, we consider a more practical but challenging setting where the source domain data is unavailable and the target domain data is unlabeled. Specifically, we address the domain discrepancy problem from the perspective of contrastive learning. The key idea of our work is to learn a domain-invariant feature by 1) performing clustering directly in the original feature space with nearest neighbors; 2) constructing truly hard negative pairs by extended neighbors without introducing additional computational complexity; and 3) combining noise-contrastive estimation theory to gain computational advantage. We conduct careful ablation studies and extensive experiments on three common benchmarks: VisDA, Office-Home, and Office-31. The results demonstrate the superiority of our methods compared with other state-of-the-art works.