Balanced Masked and Standard Face Recognition
arXiv:2110.01521
Abstract
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.
References in corpus (6)
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Deep Face Recognition: A Survey
- DropBlock: A regularization method for convolutional networks
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- YOLO5Face: Why Reinventing a Face Detector