Contrastive Adaptation Network for Unsupervised Domain Adaptation
This work improves domain adaptation for computer vision tasks by enhancing feature discriminability, though it is incremental as it builds on existing discrepancy minimization methods.
The paper tackled the problem of unsupervised domain adaptation by addressing misalignment from neglecting class information, proposing a Contrastive Adaptation Network that explicitly models intra-class and inter-class domain discrepancies, achieving state-of-the-art performance on Office-31 and VisDA-2017 benchmarks.
Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may lead to misalignment and poor generalization performance. To address this issue, this paper proposes Contrastive Adaptation Network (CAN) optimizing a new metric which explicitly models the intra-class domain discrepancy and the inter-class domain discrepancy. We design an alternating update strategy for training CAN in an end-to-end manner. Experiments on two real-world benchmarks Office-31 and VisDA-2017 demonstrate that CAN performs favorably against the state-of-the-art methods and produces more discriminative features.