# SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition

arXiv: https://arxiv.org/abs/2205.12010 · HTML: https://mlsanity.com/paper/2205.12010/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Range Loss for Deep Face Recognition with Long-tail](https://mlsanity.com/paper/1611.08976/) (2016)
- [L2-constrained Softmax Loss for Discriminative Face Verification](https://mlsanity.com/paper/1703.09507/) (2017)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [Learning towards Minimum Hyperspherical Energy](https://mlsanity.com/paper/1805.09298/) (2018)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [Mis-classified Vector Guided Softmax Loss for Face Recognition](https://mlsanity.com/paper/1912.00833/) (2019)
- [Neural Aggregation Network for Video Face Recognition](https://mlsanity.com/paper/1603.05474/) (2016)
- [Level Playing Field for Million Scale Face Recognition](https://mlsanity.com/paper/1705.00393/) (2017)
- [Ring loss: Convex Feature Normalization for Face Recognition](https://mlsanity.com/paper/1803.00130/) (2018)
- [Surpassing Human-Level Face Verification Performance on LFW with GaussianFace](https://mlsanity.com/paper/1404.3840/) (2014)
- [Noise-Tolerant Paradigm for Training Face Recognition CNNs](https://mlsanity.com/paper/1903.10357/) (2019)
- [Targeting Ultimate Accuracy: Face Recognition via Deep Embedding](https://mlsanity.com/paper/1506.07310/) (2015)
- [P2SGrad: Refined Gradients for Optimizing Deep Face Models](https://mlsanity.com/paper/1905.02479/) (2019)
- [Template Adaptation for Face Verification and Identification](https://mlsanity.com/paper/1603.03958/) (2016)
- [Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition](https://mlsanity.com/paper/1804.01159/) (2018)

## Built on by (most cited first, 21 of 21)

- [Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network](https://mlsanity.com/paper/2407.19768/) (2024)
- [Pluralistic Aging Diffusion Autoencoder](https://mlsanity.com/paper/2303.11086/) (2023)
- [Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network](https://mlsanity.com/paper/2212.14181/) (2022)
- [Surveillance Face Anti-spoofing](https://mlsanity.com/paper/2301.00975/) (2023)
- [Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning](https://mlsanity.com/paper/2402.06223/) (2024)
- [DiffAge3D: Diffusion-based 3D-aware Face Aging](https://mlsanity.com/paper/2408.15922/) (2024)
- [Surveillance Face Presentation Attack Detection Challenge](https://mlsanity.com/paper/2304.07580/) (2023)
- [AdvCloak: Customized Adversarial Cloak for Privacy Protection](https://mlsanity.com/paper/2312.14407/) (2023)
- [Dealing with Subject Similarity in Differential Morphing Attack Detection](https://mlsanity.com/paper/2404.07667/) (2024)
- [StableMorph: High-Quality Face Morph Generation with Stable Diffusion](https://mlsanity.com/paper/2511.08090/) (2025)
- [Ensemble Learning using Transformers and Convolutional Networks for Masked Face Recognition](https://mlsanity.com/paper/2210.04816/) (2022)
- [Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation](https://mlsanity.com/paper/2401.01575/) (2024)
- [Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay](https://mlsanity.com/paper/2503.16432/) (2025)
- [Just Noticeable Difference Modeling for Face Recognition System](https://mlsanity.com/paper/2209.05856/) (2022)
- [Distributional Estimation of Data Uncertainty for Surveillance Face Anti-spoofing](https://mlsanity.com/paper/2309.09485/) (2023)
- [Identification of Conversation Partners from Egocentric Video](https://mlsanity.com/paper/2406.08089/) (2024)
- [An Embedded Intelligent System for Attendance Monitoring](https://mlsanity.com/paper/2406.13694/) (2024)
- [FaceQSORT: a Multi-Face Tracking Method based on Biometric and Appearance Features](https://mlsanity.com/paper/2501.11741/) (2025)
- [Personalized Face Privacy Protection From a Single Image](https://mlsanity.com/paper/2605.19032/) (2026)
- [Intentional Electromagnetic Interference Attacks on Facial Recognition](https://mlsanity.com/paper/2607.15512/) (2026)
- [Quality-Aware Multimodal Fusion Reveals Implicit Identity in Valence-Arousal Features](https://mlsanity.com/paper/2607.21347/) (2026)

## Abstract (arXiv)

Deep face recognition has achieved great success due to large-scale training databases and rapidly developing loss functions. The existing algorithms devote to realizing an ideal idea: minimizing the intra-class distance and maximizing the inter-class distance. However, they may neglect that there are also low quality training images which should not be optimized in this strict way. Considering the imperfection of training databases, we propose that intra-class and inter-class objectives can be optimized in a moderate way to mitigate overfitting problem, and further propose a novel loss function, named sigmoid-constrained hypersphere loss (SFace). Specifically, SFace imposes intra-class and inter-class constraints on a hypersphere manifold, which are controlled by two sigmoid gradient re-scale functions respectively. The sigmoid curves precisely re-scale the intra-class and inter-class gradients so that training samples can be optimized to some degree. Therefore, SFace can make a better balance between decreasing the intra-class distances for clean examples and preventing overfitting to the label noise, and contributes more robust deep face recognition models. Extensive experiments of models trained on CASIA-WebFace, VGGFace2, and MS-Celeb-1M databases, and evaluated on several face recognition benchmarks, such as LFW, MegaFace and IJB-C databases, have demonstrated the superiority of SFace.