SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition

Abstract

Deep face recognition has achieved great success due to large-scale training databases and rapidly developing loss functions. The existing algorithms devote to realizing an ideal idea: minimizing the intra-class distance and maximizing the inter-class distance. However, they may neglect that there are also low quality training images which should not be optimized in this strict way. Considering the imperfection of training databases, we propose that intra-class and inter-class objectives can be optimized in a moderate way to mitigate overfitting problem, and further propose a novel loss function, named sigmoid-constrained hypersphere loss (SFace). Specifically, SFace imposes intra-class and inter-class constraints on a hypersphere manifold, which are controlled by two sigmoid gradient re-scale functions respectively. The sigmoid curves precisely re-scale the intra-class and inter-class gradients so that training samples can be optimized to some degree. Therefore, SFace can make a better balance between decreasing the intra-class distances for clean examples and preventing overfitting to the label noise, and contributes more robust deep face recognition models. Extensive experiments of models trained on CASIA-WebFace, VGGFace2, and MS-Celeb-1M databases, and evaluated on several face recognition benchmarks, such as LFW, MegaFace and IJB-C databases, have demonstrated the superiority of SFace.

arXiv comment12 pages, 9 figures

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Deep Learning Face Representation by Joint Identification-Verification
• Learning Face Representation from Scratch
• NormFace: L2 Hypersphere Embedding for Face Verification
• Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
• L2-constrained Softmax Loss for Discriminative Face Verification
• Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
• Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?
• Multicolumn Networks for Face Recognition
• Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
• Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning

Cited by in corpus (5)

• OPOM: Customized Invisible Cloak towards Face Privacy Protection
• Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
• Prototype Memory for Large-scale Face Representation Learning
• SDGMNet: Statistic-based Dynamic Gradient Modulation for Local Descriptor Learning
• MLFW: A Database for Face Recognition on Masked Faces