Semantic Concentration for Domain Adaptation

by   Shuang Li, et al.

Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature distributions of the two domains. However, the majority of them focus on the entire image features where irrelevant semantic information, e.g., the messy background, is inevitably embedded. Enforcing feature alignments in such case will negatively influence the correct matching of objects and consequently lead to the semantically negative transfer due to the confusion of irrelevant semantics. To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions. Specifically, we train the classifier to class-wisely maximize the prediction distribution divergence of each sample pair, which enables the model to find the region with large differences among the same class of samples. Meanwhile, the feature extractor attempts to minimize that discrepancy, which suppresses the features of dissimilar regions among the same class of samples and accentuates the features of principal parts. As a general method, SCDA can be easily integrated into various DA methods as a regularizer to further boost their performance. Extensive experiments on the cross-domain benchmarks show the efficacy of SCDA.


page 7

page 8


Discriminative Label Consistent Domain Adaptation

Domain adaptation (DA) is transfer learning which aims to learn an effec...

Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation

Partial domain adaptation (PDA) attracts appealing attention as it deals...

Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA), which aims to explore the transfer...

Low-confidence Samples Matter for Domain Adaptation

Domain adaptation (DA) aims to transfer knowledge from a label-rich sour...

Transferable Semantic Augmentation for Domain Adaptation

Domain adaptation has been widely explored by transferring the knowledge...

Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation

Domain adaptation (DA) becomes an up-and-coming technique to address the...

Attention Regularized Laplace Graph for Domain Adaptation

In leveraging manifold learning in domain adaptation (DA), graph embeddi...

Please sign up or login with your details

Forgot password? Click here to reset