Bidirectional View based Consistency Regularization for Semi-Supervised Domain Adaptation

Published: 26 Mar 2023, Last Modified: 26 Mar 2023Accepted by TMLREveryoneRevisionsBibTeX
Abstract: Distinguished from unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA) could access a few labeled target samples during learning additionally. Although achieving remarkable progress, target supervised information is easily overwhelmed by massive source supervised information, as there are many more labeled source samples than those in the target domain. In this work, we propose a novel method BVCR that better utilizes the supervised information by three schemes, i.e., modeling, exploration, and interaction. In the modeling scheme, BVCR models the source supervision and target supervision separately to avoid target supervised information being overwhelmed by source supervised information and better utilize the target supervision. Besides, as both supervised information naturally offer distinct views for the target domain, the exploration scheme performs intra-domain consistency regularization to better explore target information with bidirectional views. Moreover, as both views are complementary to each other, the interaction scheme introduces inter-domain consistency regularization to activate information interaction bidirectionally. Thus, the proposed method is elegantly symmetrical by design and easy to implement. Extensive experiments are conducted, and the results show the effectiveness of the proposed method.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Frederic_Sala1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 578