DOMAIN ADAPTING ABILITY OF SELF-SUPERVISED LEARNING FOR FACE RECOGNITION

Chun Hsien Lin, Bing-Fei Wu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the learned models degenerate in a testing scenario (target domain). In face recognition tasks, classes in two domains are usually different, so classical domain adaptation approaches, assuming there are shared classes in domains, may not be reasonable solutions for this problem. In this paper, self-supervised learning is adopted to learn a better embedding space where the subjects in target domain are more distinguishable. The learning goal is maximizing the similarity between the embeddings of each image and its mirror in both domains. The experiments show its competitive results compared with prior works. To know the reason why it can achieve such performance, we further discuss how this approach affects the learning of embeddings.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PublisherIEEE Computer Society
Pages479-483
Number of pages5
ISBN (Electronic)9781665441155
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
Duration: 19 Sep 202122 Sep 2021

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2021-September
ISSN (Print)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing, ICIP 2021
Country/TerritoryUnited States
CityAnchorage
Period19/09/2122/09/21

Keywords

  • Domain adaptation
  • Face recognition
  • Self-supervised learning

Fingerprint

Dive into the research topics of 'DOMAIN ADAPTING ABILITY OF SELF-SUPERVISED LEARNING FOR FACE RECOGNITION'. Together they form a unique fingerprint.

Cite this