Learning adaptive geometry for unsupervised domain adaptation

Baoyao Yang, Pong Chi YUEN*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Unsupervised domain adaptation is an effective approach to solve the problem of dataset bias. However, most existing unsupervised domain adaptation methods assume that the geometry structures of data distributions are similar in the source and target domains. This assumption is invalid in many practical applications, because the training and test datasets usually differ in the variability modes and/or variation degrees. This paper handles the problem of inconsistent geometries by aligning both data representations and geometries. To overcome the lack of target labels in aligning geometries, this paper proposes learning the adaptive geometry that is derived from the domain-shared label space. Source and target geometries are aligned by constraining them with the unified criteria of the adaptive geometry. Combining the adaptive geometry learning and adversarial learning techniques, we develop a geometry-aware dual-stream network to learn the geometry-aligned representations. Experimental results show that our method achieves good performance on cross-dataset recognition tasks.

Original languageEnglish
Article number107638
JournalPattern Recognition
Volume110
DOIs
Publication statusPublished - Feb 2021

Scopus Subject Areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

User-Defined Keywords

  • Distribution alignment
  • Domain adaptation
  • Manifold structure

Fingerprint

Dive into the research topics of 'Learning adaptive geometry for unsupervised domain adaptation'. Together they form a unique fingerprint.

Cite this