PLFace: Progressive Learning for Face Recognition with Mask Bias

Abstract

The outbreak of the COVID-19 coronavirus epidemic has promoted the development of masked face recognition (MFR). Nevertheless, the performance of regular face recognition is severely compromised when the MFR accuracy is blindly pursued. More facts indicate that MFR should be regarded as a mask bias of face recognition rather than an independent task. To mitigate mask bias, we propose a novel Progressive Learning Loss (PLFace) that achieves a progressive training strategy for deep face recognition to learn balanced performance for masked/mask-free faces recognition based on margin losses. Particularly, our PLFace adaptively adjusts the relative importance of masked and mask-free samples during different training stages. In the early stage of training, PLFace mainly learns the feature representations of mask-free samples. At this time, the regular sample embeddings shrink to the corresponding prototype, which represents the center of each class while being stored in the last linear layer. In the later stage of training, PLFace converges on mask-free samples and further focuses on masked samples until the masked sample embeddings are also gathered in the center of the class. The entire training process emphasizes the paradigm that normal samples shrink first and masked samples gather afterward. Extensive experimental results on popular regular and masked face benchmarks demonstrate that our proposed PLFace can effectively eliminate mask bias in face recognition. Compared to state-of-the-art competitors, PLFace significantly improves the accuracy of MFR while maintaining the performance of normal face recognition.