SphereFace: Deep Hypersphere Embedding for Face Recognition (2017-04-26T00:00:00.000000Z)

TL;DR

This paper proposes the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features in deep face recognition (FR) problem under open-set protocol.

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 1 show the superiority of A-Softmax loss in FR tasks.

Authors

Yandong Wen

4 papers

B. Raj

7 papers

Le Song

8 papers

TL;DR

Abstract

Authors

References41 items

A Discriminative Feature Learning Approach for Deep Face Recognition

Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition

Large-Margin Softmax Loss for Convolutional Neural Networks

Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

Deep Residual Learning for Image Recognition

Sparsifying Neural Network Connections for Face Recognition

The MegaFace Benchmark: 1 Million Faces for Recognition at Scale

Deep Metric Learning via Lifted Structured Feature Embedding

Robust Face Recognition via Multimodal Deep Face Representation

Targeting Ultimate Accuracy: Face Recognition via Deep Embedding

Multi-manifold deep metric learning for image set classification

MegaFace: A Million Faces for Recognition at Scale

FaceNet: A unified embedding for face recognition and clustering

DeepID3: Face Recognition with Very Deep Neural Networks

Deep Metric Learning Using Triplet Network

Deeply learned face representations are sparse, selective, and robust

Learning Face Representation from Scratch

A data-driven approach to cleaning large face datasets

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

Deep Learning Face Representation from Predicting 10,000 Classes

Discriminative Deep Metric Learning for Face Verification in the Wild

Caffe: Convolutional Architecture for Fast Feature Embedding

Deep Learning Face Representation by Joint Identification-Verification

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

Learning Fine-Grained Image Similarity with Deep Ranking

ImageNet classification with deep convolutional neural networks

Large scale metric learning from equivalence constraints

Face recognition in unconstrained videos with matched background similarity

Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments

Large-scale manifold learning

Dimensionality Reduction by Learning an Invariant Mapping

Distance Metric Learning for Large Margin Nearest Neighbor Classification

Learning a similarity metric discriminatively, with application to face verification

Face recognition using Laplacianfaces

Multimodal biometrics: An overview

Video-based face recognition using probabilistic appearance manifolds

Deep Face Recognition

Labeled Faces in the Wild : Updates and New Reporting Procedures

Distance Metric Learning with Eigenvalue Optimization

Distance Metric Learning with Application to Clustering with Side-Information

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names