Mitigating domain mismatch in face recognition using style matching

Chun Hsien Lin*, Bing Fei Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Despite outstanding performance on public benchmarks, face recognition still suffers due to domain mismatch between training (source) and testing (target) data. Furthermore, these domains are not shared classes, which complicates domain adaptation. Since this is also a fine-grained classification problem which does not strictly follow the low-density separation principle, conventional domain adaptation approaches do not resolve these problems. In this paper, we formulate domain mismatch in face recognition as a style mismatch problem for which we propose two methods. First, we design a domain discriminator with human-level judgment to mine target-like images in the training data to mitigate the domain gap. Second, we extract style representations in low-level feature maps of the backbone model, and match the style distributions of the two domains to find a common style representation. Evaluations on verification and open-set and closed-set identification protocols show that both methods yield good improvements, and that performance is more robust if they are combined. Our approach is competitive with related work, and its effectiveness is verified in a practical application.

Original languageEnglish
Pages (from-to)9-21
Number of pages13
JournalNeurocomputing
Volume487
DOIs
StatePublished - 28 May 2022

Keywords

  • Domain adaptation
  • Face recognition
  • Optimal transport
  • Sinkhorn algorithm
  • Style transfer

Fingerprint

Dive into the research topics of 'Mitigating domain mismatch in face recognition using style matching'. Together they form a unique fingerprint.

Cite this