Balanced Masked and Standard Face Recognition
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 how to have a balanced performance of masked and standard face recognition. In order to prevent the overfitting for the masked face recognition, we balance 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, and face alignment using YOLO5Face. With this strategy, we achieve good and balanced performance for both masked and standard face recognition.