Learning to resolve uncertainties for large-scale face recognition

Facial recognition is a category of biometric security, used widely in various industries where we identify and authenticate an individuals identity using their face. In the modern deep learning era, face recognition datasets are playing a significant role in achieving state-of-the-art accuracy by acquiring and training millions of face images. Annotating such a large-scale face recognition dataset is challenging due to low-quality face images, and incorrect annotations unknowingly made by annotators. Training a deep learning model with such uncertainties leads to deep model overfitting on noisy uncertain samples and degradation of the discriminative ability of the model. To address these issues, we propose a simple yet effective uncertainty learning network that efficiently reduces over-fitting caused by uncertain face images. More specifically, our FC module weights each sample in the mini-batch at the decision layer, and relabeling mechanism carefully modify the labels of incorrect samples in the mini- batch. Results on UB-B, UB-C, LFW, AgeDB30, CFP-FP, CALFW and CPLFW public datasets demonstrate that our approach achieves state-of-the-art performance (C) 2022 Published by Elsevier B.V.

Automated summary

Facial recognition is a crucial biometric security technology in the era of deep learning. However, annotating large-scale face recognition datasets becomes challenging due to uncertainties in face images and incorrect annotations. To address these issues, we propose an effective uncertainty learning network that reduces overfitting effectively.