MagFace: A Universal Representation for Face Recognition and Quality Assessment

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 o...

Full description

Saved in:
Bibliographic Details
Published inProceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 14220 - 14229
Main Authors Meng, Qiang, Zhao, Shichao, Huang, Zhida, Zhou, Feng
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2021
Subjects
Computer vision
Face recognition
Loss measurement
Noise measurement
Object recognition
Quality assessment
Uncertainty
Online AccessGet full text

Cover

More Information
Summary: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, Mag-Face introduces an adaptive mechanism to learn a well-structured 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.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.01400