English

SphereFace Revived: Unifying Hyperspherical Face Recognition

Computer Vision and Pattern Recognition 2022-03-17 v3 Artificial Intelligence Machine Learning

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.

Keywords

Cite

@article{arxiv.2109.05565,
  title  = {SphereFace Revived: Unifying Hyperspherical Face Recognition},
  author = {Weiyang Liu and Yandong Wen and Bhiksha Raj and Rita Singh and Adrian Weller},
  journal= {arXiv preprint arXiv:2109.05565},
  year   = {2022}
}

Comments

Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence

R2 v1 2026-06-24T05:53:47.596Z