Domain Attention Consistency for Multi-Source Domain Adaptation

Zhongying Deng, Kaiyang Zhou, Yongxin Yang, Tao Xiang

Research output: Contribution to conferenceConference paperpeer-review

6 Citations (Scopus)

Abstract

Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrowed from the single source setting. However, with diverse source domains, aligning pairwise feature distributions is challenging and could even be counterproductive for MSDA. In this paper, we introduce a novel approach: transferable attribute learning. The motivation is simple: although different domains can have drastically different visual appearances, they contain the same set of classes characterized by the same set of attributes; an MSDA model thus should focus on learning the most transferable attributes for the target domain. Adopting this approach, we propose a domain attention consistency network, dubbed DAC-Net. The key design is a feature channel attention module, which aims to identify transferable features (attributes). Importantly, the attention module is supervised by a consistency loss, which is imposed on the distributions of channel attention weights between source and target domains. Moreover, to facilitate discriminative feature learning on the target data, we combine pseudo-labeling with a class compactness loss to minimize the distance between the target features and the classifier's weight vectors. Extensive experiments on three MSDA benchmarks show that our DAC-Net achieves new state of the art performance on all of them.

Original languageEnglish
Pages1-13
Number of pages13
Publication statusPublished - Nov 2021
Event32nd British Machine Vision Conference, BMVC 2021 - Virtual, Online
Duration: 22 Nov 202125 Nov 2021
https://www.bmvc2021-virtualconference.com/
https://www.bmvc2021-virtualconference.com/programme/accepted-papers/

Conference

Conference32nd British Machine Vision Conference, BMVC 2021
Period22/11/2125/11/21
Internet address

Scopus Subject Areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Domain Attention Consistency for Multi-Source Domain Adaptation'. Together they form a unique fingerprint.

Cite this