×

SphereFace

swMATH ID: 39108
Software Authors: Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, Le Song
Description: SphereFace: Deep Hypersphere Embedding for Face Recognition. This paper addresses deep face recognition (FR) problem under 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. However, few existing algorithms can effectively achieve this criterion. To this end, we propose the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features. Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold. Moreover, the size of angular margin can be quantitatively adjusted by a parameter m. We further derive specific m to approximate the ideal feature criterion. Extensive analysis and experiments on Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace Challenge show the superiority of A-Softmax loss in FR tasks. The code has also been made publicly available.
Homepage: https://arxiv.org/abs/1704.08063
Related Software: CosFace; ImageNet; DeepID3; DeepFace; ShuffleNet; AdaCos; FaceNet; VGGFace2; ArcFace; PyTorch; AlexNet; Caffe; MagFace; EfficientNet; FaceX-Zoo; AttentionNet; CPLFW; WebFace260M; CASIA-SURF; SGDR
Referenced in: 2 Publications

Referenced in 1 Field

2 Computer science (68-XX)

Referencing Publications by Year