# MagFace: A Universal Representation for Face Recognition and Quality Assessment

arXiv: https://arxiv.org/abs/2103.06627 · HTML: https://mlsanity.com/paper/2103.06627/

## Key facts

- Cited by 334 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 11 Mar 2021.

## Builds on (most cited first, 24 of 24)

- [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)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [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)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [Data Uncertainty Learning in Face Recognition](https://mlsanity.com/paper/2003.11339/) (2020)
- [SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness](https://mlsanity.com/paper/2003.09373/) (2020)
- [Deep Metric Learning with Angular Loss](https://mlsanity.com/paper/1708.01682/) (2017)
- [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)
- [Face Image Quality Assessment: A Literature Survey](https://mlsanity.com/paper/2009.01103/) (2020)
- [DeepID3: Face Recognition with Very Deep Neural Networks](https://mlsanity.com/paper/1502.00873/) (2015)
- [FaceQnet: Quality Assessment for Face Recognition based on Deep Learning](https://mlsanity.com/paper/1904.01740/) (2019)
- [Learning Meta Face Recognition in Unseen Domains](https://mlsanity.com/paper/2003.07733/) (2020)
- [Learning to Cluster Faces via Confidence and Connectivity Estimation](https://mlsanity.com/paper/2004.00445/) (2020)
- [The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances](https://mlsanity.com/paper/2009.13290/) (2020)
- [Support Vector Guided Softmax Loss for Face Recognition](https://mlsanity.com/paper/1812.11317/) (2018)
- [Feature Incay for Representation Regularization](https://mlsanity.com/paper/1705.10284/) (2017)

## Built on by (most cited first, 30 of 334)

- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability](https://mlsanity.com/paper/2112.06592/) (2021)
- [Residual Denoising Diffusion Models](https://mlsanity.com/paper/2308.13712/) (2023)
- [Physical Adversarial Attack meets Computer Vision: A Decade Survey](https://mlsanity.com/paper/2209.15179/) (2022)
- [Real-Time Radiance Fields for Single-Image Portrait View Synthesis](https://mlsanity.com/paper/2305.02310/) (2023)
- [Generalizable Synthetic Image Detection via Language-guided Contrastive Learning](https://mlsanity.com/paper/2305.13800/) (2023)
- [GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations](https://mlsanity.com/paper/2305.19962/) (2023)
- [Data Poisoning Won't Save You From Facial Recognition](https://mlsanity.com/paper/2106.14851/) (2021)
- [Voice-Face Homogeneity Tells Deepfake](https://mlsanity.com/paper/2203.02195/) (2022)
- [KeyPoint Relative Position Encoding for Face Recognition](https://mlsanity.com/paper/2403.14852/) (2024)
- [Learning Compatible Embeddings](https://mlsanity.com/paper/2108.01958/) (2021)
- [PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation](https://mlsanity.com/paper/2108.10710/) (2021)
- [Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/2108.10290/) (2021)
- [EdgeFace: Efficient Face Recognition Model for Edge Devices](https://mlsanity.com/paper/2307.01838/) (2023)
- [It's All About Your Sketch: Democratising Sketch Control in Diffusion Models](https://mlsanity.com/paper/2403.07234/) (2024)
- [SDFR: Synthetic Data for Face Recognition Competition](https://mlsanity.com/paper/2404.04580/) (2024)
- [Understanding the Feature Norm for Out-of-Distribution Detection](https://mlsanity.com/paper/2310.05316/) (2023)
- [Face.evoLVe: A High-Performance Face Recognition Library](https://mlsanity.com/paper/2107.08621/) (2021)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [QMagFace: Simple and Accurate Quality-Aware Face Recognition](https://mlsanity.com/paper/2111.13475/) (2021)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2305.05768/) (2023)
- [FRoundation: Are Foundation Models Ready for Face Recognition?](https://mlsanity.com/paper/2410.23831/) (2024)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [Cluster and Aggregate: Face Recognition with Large Probe Set](https://mlsanity.com/paper/2210.10864/) (2022)
- [TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security](https://mlsanity.com/paper/2308.10133/) (2023)
- [Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection](https://mlsanity.com/paper/2304.05096/) (2023)
- [Label-Only Model Inversion Attacks via Knowledge Transfer](https://mlsanity.com/paper/2310.19342/) (2023)

## Abstract (arXiv)

The performance of face recognition system degrades when the variability of the acquired faces increases. Prior work alleviates this issue by either monitoring the face quality in pre-processing or predicting the data uncertainty along with the face feature. This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face. Under the new loss, it can be proven that the magnitude of the feature embedding monotonically increases if the subject is more likely to be recognized. In addition, MagFace introduces an adaptive mechanism to learn a wellstructured within-class feature distributions by pulling easy samples to class centers while pushing hard samples away. This prevents models from overfitting on noisy low-quality samples and improves face recognition in the wild. Extensive experiments conducted on face recognition, quality assessments as well as clustering demonstrate its superiority over state-of-the-arts. The code is available at https://github.com/IrvingMeng/MagFace.