SphereFace Revived: Unifying Hyperspherical Face Recognition

TL;DR

This paper improves hyperspherical face recognition by introducing SphereFace-R, a more stable and effective variant of SphereFace, through novel margin implementation and training stabilization techniques, achieving competitive results.

Contribution

The paper presents SphereFace-R, a stabilized and enhanced hyperspherical face recognition method with novel margin implementation and training strategies.

Findings

SphereFace-R outperforms or matches state-of-the-art methods.

Training stability is significantly improved with the proposed strategies.

Different feature normalization schemes are studied for optimal performance.

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.