SphereFace: Deep Hypersphere Embedding for Face Recognition

TL;DR

This paper introduces the A-Softmax loss function that enables CNNs to learn angularly discriminative face features on a hypersphere, significantly improving open-set face recognition performance.

Contribution

It proposes the angular softmax loss that enforces angular margins on a hypersphere, enhancing discriminative feature learning for face recognition.

Findings

A-Softmax loss outperforms existing methods on LFW, YTF, and MegaFace.

The angular margin parameter $m$ can be tuned for optimal discrimination.

Extensive experiments validate the effectiveness of the proposed approach.

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.