SOTAVerified

SphereFace: Deep Hypersphere Embedding for Face Recognition

2017-04-26CVPR 2017Code Available0· sign in to hype

Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, Le Song

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Tasks

Face IdentificationFace RecognitionFace Verification

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CK+SphereFaceAccuracy93.8—Unverified
MegaFaceSphereFace (3-patch ensemble)Accuracy89.14—Unverified
MegaFaceSphereFace (single model)Accuracy85.56—Unverified
Trillion Pairs DatasetA-SoftmaxAccuracy43.76—Unverified
YouTube Faces DBSphereFaceAccuracy95—Unverified

Reproductions