One-Shot Face Recognition through a Region Inception ResNet with Modified Triplet Loss

Abstract

Face recognition has become a convenient method for identity verification, especially the one-shot task has much practical value. Some former works have achieved considerable results. However, they perform ill under the situation of COVID-19 with more and more people wearing a mask. This requires the extracted face features distinguishable and robust enough for classifying different masked people. It is difficult for the one-shot task with only one sample for training. To solve this problem, we designed a network called Region Inception ResNet with Modified Triplet Loss, which generates robust features. It keeps high accuracy even under masked condition. The networks are trained on the datasets of CASIA-Webface and Ms-Celeb-1M, tested on LFW (Labelled Faces in the Wild). Experiments in Section 6 show the effectiveness of our method.