SphereFace Revived : Unifying Hyperspherical Face Recognition

This paper addresses the deep face recognition problem under an open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. To this end, hyperspherical face recognition, as a promising...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 2 vom: 31. Feb., Seite 2458-2474
Auteur principal: Liu, Weiyang (Auteur)
Autres auteurs: Wen, Yandong, Raj, Bhiksha, Singh, Rita, Weller, Adrian
Format: Article en ligne
Langue:English
Publié: 2023
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
Description
Résumé:This paper addresses the deep face recognition problem under an open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. To this end, hyperspherical face recognition, as a promising line of research, has attracted increasing attention and gradually become a major focus in face recognition research. As one of the earliest works in hyperspherical face recognition, SphereFace explicitly proposed to learn face embeddings with large inter-class angular margin. However, SphereFace still suffers from severe training instability which limits its application in practice. In order to address this problem, we introduce a unified framework to understand large angular margin in hyperspherical face recognition. Under this framework, we extend the study of SphereFace and propose an improved variant with substantially better training stability - SphereFace-R. Specifically, we propose two novel ways to implement the multiplicative margin, and study SphereFace-R under three different feature normalization schemes (no feature normalization, hard feature normalization and soft feature normalization). We also propose an implementation strategy - "characteristic gradient detachment" - to stabilize training. Extensive experiments on SphereFace-R show that it is consistently better than or competitive with state-of-the-art methods
Description:Date Completed 06.04.2023
Date Revised 06.04.2023
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1939-3539
DOI:10.1109/TPAMI.2022.3159732