Balanced Masked and Standard Face Recognition
This work addresses the domain-specific problem of masked face recognition for applications like security and surveillance, but it is incremental as it builds on existing methods with minor modifications.
The authors tackled the problem of achieving balanced performance in both masked and standard face recognition by controlling the proportion of masked faces in training data to prevent overfitting. They achieved good and balanced performance through improved network architecture, data augmentation, and training strategies.
We present the improved network architecture, data augmentation, and training strategies for the Webface track and Insightface/Glint360K track of the masked face recognition challenge of ICCV2021. One of the key goals is to have a balanced performance of masked and standard face recognition. In order to prevent the overfitting for the masked face recognition, we control the total number of masked faces by not more than 10\% of the total face recognition in the training dataset. We propose a few key changes to the face recognition network including a new stem unit, drop block, face detection and alignment using YOLO5Face, feature concatenation, a cycle cosine learning rate, etc. With this strategy, we achieve good and balanced performance for both masked and standard face recognition.