Domain Alignment Embedding Network for Sketch Face Recognition

Abstract

Sketch face recognition refers to the process of matching sketches to photos. Recently, there has been a growing interest in using deep learning to learn discriminative features for sketch face recognition. However, the success of deep learning relies on the large-scale paired images to counteract effects such as over-fitting, since the amount of the paired training data is relatively small, the discriminative power of the deeply learned features will inevitably be reduced. This paper proposes a novel deep metric learning method termed domain alignment embedding network for sketch face recognition. Specifically, a training episode strategy is designed to alleviate the small sample problem, and a domain alignment embedding loss is proposed to guide the feature embedding network to learn discriminative features. Extensive experimental results on the UoM-SGFSv2 and PRIP-VSGC datasets are verified to show the effectiveness of the proposed method.