Data to 7 Oct 2026

SphereFace: Deep Hypersphere Embedding for Face Recognition

arXiv 1704.08063 ↗First posted 26 Apr 2017cs.CVcited by 733

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 733 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 226; 2022: 153; 2023: 127; 2024: 107; 2025: 74; 2026: 46.

733 papers.

Sort:

By area:

2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 221
2021Open-World Semi-Supervised Learningcited by 165
2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 109
2023EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognitioncited by 109
2021SynFace: Face Recognition with Synthetic Datacited by 106

38 more

2021Evidential Deep Learning for Open Set Action Recognitioncited by 96
2022Neural Collapse: A Review on Modelling Principles and Generalizationcited by 95
2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
2021Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognitioncited by 89
2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
2022Are All Losses Created Equal: A Neural Collapse Perspectivecited by 78
2022Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FCcited by 73
2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 68
2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 67
2022PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognitioncited by 67
2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
2021Neural Re-Rendering of Humans from a Single Imagecited by 59
2021Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognitioncited by 55
2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53
2022Meta Balanced Network for Fair Face Recognitioncited by 53
2021Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuningcited by 50
2022Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifoldcited by 50
2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
2022POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognitioncited by 49
2021HumanGAN: A Generative Model of Humans Imagescited by 47
2024UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalizationcited by 46
2021Face Transformer for Recognitioncited by 45
2021Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGANcited by 45
2021Orthogonal Projection Losscited by 44
2021One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objectivecited by 43
2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
2021Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentationcited by 41
2021Masked Face Recognition Challenge: The InsightFace Track Reportcited by 41
2022WebFace260M: A Benchmark for Million-Scale Deep Face Recognitioncited by 41
2021Consistent Instance False Positive Improves Fairness in Face Recognitioncited by 40
2021Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspectivecited by 39
2021Few-Shot Object Detection via Association and DIscriminationcited by 39
2021PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognitioncited by 38
2023SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimationcited by 38

50 most cited of 733 All 733 (JSON)