English

Towards Large-scale Masked Face Recognition

Computer Vision and Pattern Recognition 2023-10-26 v1

Abstract

During the COVID-19 coronavirus epidemic, almost everyone is wearing masks, which poses a huge challenge for deep learning-based face recognition algorithms. In this paper, we will present our \textbf{championship} solutions in ICCV MFR WebFace260M and InsightFace unconstrained tracks. We will focus on four challenges in large-scale masked face recognition, i.e., super-large scale training, data noise handling, masked and non-masked face recognition accuracy balancing, and how to design inference-friendly model architecture. We hope that the discussion on these four aspects can guide future research towards more robust masked face recognition systems.

Keywords

Cite

@article{arxiv.2310.16364,
  title  = {Towards Large-scale Masked Face Recognition},
  author = {Manyuan Zhang and Bingqi Ma and Guanglu Song and Yunxiao Wang and Hongsheng Li and Yu Liu},
  journal= {arXiv preprint arXiv:2310.16364},
  year   = {2023}
}

Comments

the top1 solution for ICCV2021-MFR challenge

R2 v1 2026-06-28T13:01:04.534Z