Open AccessMsrFace: Multi-Sphere Radius Loss for Deep Face Recognition
Author(s) -
Xueming Du,
Xiaoxuan Han,
Yu Qin,
Dong Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1601/5/052007
Subject(s) - discriminative model , radius , face (sociological concept) , facial recognition system , computer science , artificial intelligence , focus (optics) , pattern recognition (psychology) , mathematics , physics , optics , computer security , social science , sociology
Loss functions is one of the main challenges in face recognition problems. Recent works focus on designing loss functions that make learned features more discriminative by a larger angular or cosine distance. In this paper, in addition to the method based on additional angle margins, we propose a Multi-Sphere Radius Loss (MsrFace) to add radius constraints. MsrFace pushes learned features to hyperspheres with different spherical radii and the classes can be separated more strictly. We present experiments on several widely used benchmarks to show that MsrFace has a better performance in comparison with some recent state-of-the-art face recognition methods.