MagFace: A Universal Representation for Face Recognition and Quality Assessment

Feng Zhou, Qiang Meng, Zhida Huang, Shichao Zhao

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• IrvingMeng/MagFace — marked official in Papers with Code; named in the paper
• leondgarse/Keras_insightface

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.06627")
get_code_for_paper("2103.06627")
have("2103.06627")

Connect an agent — have() is free.