Towards Large-scale Masked Face Recognition
This addresses the practical problem of masked face recognition for real-world applications during the pandemic, but appears incremental as it builds on existing deep learning methods.
The paper tackles the challenge of face recognition when people wear masks during COVID-19, presenting championship solutions in ICCV MFR WebFace260M and InsightFace unconstrained tracks that address large-scale training, data noise, accuracy balancing, and inference-friendly design.
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.