Generative Model Based Noise Robust Training for Unsupervised Domain Adaptation

Zhongying Deng, Da Li, Junjun He, Yi-Zhe Song, Tao Xiang

Keywords: Unsupervised Domain Adaptation, Generative Models, Feature Augmentation, Generative and Discriminative Consistency

Abstract: Target domain pseudo-labeling has shown effectiveness in unsupervised domain adaptation (UDA). However, pseudo-labels of unlabeled target domain data are inevitably noisy due to the distribution shift between source and target domains. In this paper, we propose a generative model-based noise-robust training method (GeMo-NoRT), serving for domain shift elimination and label noise robustness simultaneously. GeMo-NoRT incorporates a distribution-based class-wise feature augmentation (D-CFA) and a generative-discriminative classifier consistency (GDC), both based on the class-wise target distributions modeled by generative models. D-CFA minimizes the domain gap by augmenting the source data with distribution-sampled target features, and trains a noise-robust discriminative classifier by using target domain knowledge from the generative models. GDC regards all the class-wise generative models as a generative classifier and enforces a consistency regularization between the generative and discriminative classifiers. It exploits an ensemble of target knowledge from all the generative models to train a noise-robust discriminative classifier, and eventually gets theoretically linked to the Ben-David domain adaptation theorem for reducing domain gap. Extensive experiments on Office-Home, PACS, and Digit-Five show that our GeMo-NoRT achieves state of the art under single-source and multi-source UDA settings.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2303.05734/code)