Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
This work addresses the challenge of poor generalization in unsupervised domain adaptation for computer vision, offering incremental improvements over existing methods.
The paper tackles the problem of partial or misaligned feature distributions in unsupervised domain adaptation by proposing a Self-similarity Consistency metric to enforce cross-domain feature structure consistency and a feature norm constraint to enhance inter-class discrimination, achieving improved performance on visual domain adaptation tasks.
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains. The neglect of class information, however, may lead to partial alignment (or even misalignment) and poor generalization performance. For comprehensive alignment, we argue that the similarities across different features in the source domain should be consistent with that of in the target domain. Based on this assumption, we propose a new domain discrepancy metric, i.e., Self-similarity Consistency (SSC), to enforce the feature structure being consistent across domains. The renowned correlation alignment (CORAL) is proven to be a special case, and a sub-optimal measure of our proposed SSC. Furthermore, we also propose to mitigate the side effect of the partial alignment and misalignment by incorporating the discriminative information of the deep representations. Specifically, an embarrassingly simple and effective feature norm constraint is exploited to enlarge the discrepancy of inter-class samples. It relieves the requirements of strict alignment when performing adaptation, therefore improving the adaptation performance significantly. Extensive experiments on visual domain adaptation tasks demonstrate the effectiveness of our proposed SSC metric and feature discrimination approach.