Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MagFace: A Universal Representation for Face Recognition and Quality Assessment

About

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.

Qiang Meng, Shichao Zhao, Zhida Huang, Feng Zhou• 2021

Related benchmarks

TaskDatasetResultRank
Face VerificationLFW
Mean Accuracy99.83
339
Face VerificationAgeDB-30
Accuracy98.17
204
Face VerificationCPLFW
Accuracy92.87
188
Face VerificationIJB-C
TAR @ FAR=0.01%95.97
173
Face VerificationLFW (test)
Verification Accuracy99.83
160
Face VerificationIJB-B
TAR (FAR=1e-4)94.51
152
Face VerificationCALFW
Accuracy96.15
142
Face VerificationCFP-FP
Accuracy98.46
127
Face RecognitionCFP-FP
Accuracy98.46
66
Face VerificationAgeDB
Accuracy98.17
55
Showing 10 of 47 rows

Other info

Code

Follow for update