SphereFace Revived: Unifying Hyperspherical Face Recognition
View / Open Files
Publication Date
2022-03-16Journal Title
IEEE Transactions on Pattern Analysis and Machine Intelligence
ISSN
0162-8828
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Pages
1-1
Type
Article
This Version
AM
Metadata
Show full item recordCitation
Liu, W., Wen, Y., Raj, B., Singh, R., & Weller, A. (2022). SphereFace Revived: Unifying Hyperspherical Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-1. https://doi.org/10.1109/tpami.2022.3159732
Abstract
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
Sponsorship
Leverhulme Trust (RC-2015-067)
EPSRC (EP/V025279/1)
Identifiers
External DOI: https://doi.org/10.1109/tpami.2022.3159732
This record's URL: https://www.repository.cam.ac.uk/handle/1810/335300
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.