Log In Sign Up

MagFace: A Universal Representation for Face Recognition and Quality Assessment

by   Qiang Meng, et al.

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


page 1

page 6

page 7

page 13


AdaFace: Quality Adaptive Margin for Face Recognition

Recognition in low quality face datasets is challenging because facial a...

EQFace: A Simple Explicit Quality Network for Face Recognition

As the deep learning makes big progresses in still-image face recognitio...

Reliable Probabilistic Face Embeddings in the Wild

Probabilistic Face Embeddings (PFE) can improve face recognition perform...

Data Uncertainty Learning in Face Recognition

Modeling data uncertainty is important for noisy images, but seldom expl...

Towards Universal Representation Learning for Deep Face Recognition

Recognizing wild faces is extremely hard as they appear with all kinds o...

Cluster and Aggregate: Face Recognition with Large Probe Set

Feature fusion plays a crucial role in unconstrained face recognition wh...

OPOM: Customized Invisible Cloak towards Face Privacy Protection

While convenient in daily life, face recognition technologies also raise...

Code Repositories


MagFace: A Universal Representation for Face Recognition and Quality Assessment, CVPR2021, Oral

view repo


Implementation of related angular-margin-based classification loss functions for training (face) embedding models: SphereFace, CosFace, ArcFace and MagFace.

view repo