Adversarial Domain Adaptation via Category Transfer

Document Type

Conference Proceeding

Date of Original Version

7-1-2019

Abstract

Adversarial domain adaptation has achieved some success in learning transferable feature representations and reducing distribution discrepancy between source and target domains. However, existing approaches mainly focus on alignment of global source and target distributions without considering complex structures in categories underlying different distributions, resulting in domain confusion and the mix of distinguishable structures. In this paper, we propose an adversarial domain adaptation via category transfer (ADACT) approach for unsupervised domain adaptation (UDA). ADACT first captures multi-category information through training source and target feature generators as well as a label predictor. Secondly, it uses multi-category domain critic networks to category-wisely estimate Wasserstein distances across domains. Then it learns category-invariant feature representations by finely-grained matching different data distributions with the estimated Wasserstein distances. The adaptation can be achieved by the standard back-propagation training approach with this two-step iteration. The effectiveness of ADACT is demonstrated since it outperforms several state-of-the-art UDA methods on common domain adaptation datasets.

Publication Title, e.g., Journal

Proceedings of the International Joint Conference on Neural Networks

Volume

2019-July

Share

COinS