Domain adaptation with feature and label adversarial networks

Peng Zhao, Wenhua Zang, Bin Liu, Zhao Kang*, Kun Bai, Kaizhu Huang, Zenglin Xu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

Learning a cross-domain representation from labeled source domains to unlabeled target domains is an important research problem in representation learning. Despite the success of traditional adversarial methods, they proposed to align features from each domain only while neglecting the importance of labels, when fooling a special domain discriminator network. Thus, the discriminator of these approaches merely distinguishes whether the generated features are in-domain or not, which may lead to less class-discriminative features. In this paper, by considering the joint distributions of features and labels in both domains, we present Feature and Label Adversarial Networks (FLAN). As a result, FLAN can generate more discriminative features in both domains. Experimental results on standard unsupervised domain adaptation benchmarks have demonstrated that FLAN can outperform the state-of-art domain invariant representation learning methods.

Original languageEnglish
Pages (from-to)294-301
Number of pages8
JournalNeurocomputing
Volume439
DOIs
Publication statusPublished - 7 Jun 2021

Keywords

  • Domain adaptation
  • adversarial learning
  • classification
  • joint distribution

Fingerprint

Dive into the research topics of 'Domain adaptation with feature and label adversarial networks'. Together they form a unique fingerprint.

Cite this