Scalable Similarity-Consistent Deep Metric Learning for Face Recognition

Abstract

With the development of deep learning, deep metric learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax losses in the training process often bring large intra-class variations, and feature normalization is only exploited in the testing process to compute the pair similarities. To bridge the gap, we impose the intra-class cosine similarity between the features and weight vectors in softmax loss larger than a margin in the training step and extend it from four aspects. First, we explore the effect of a hard sample mining strategy. To alleviate the human labor of adjusting the margin hyper-parameter, a self-Adaptive margin updating strategy is proposed. Then, a normalized version is given to take full advantage of the cosine similarity constraint. Furthermore, we enhance the former constraints to consider the intra-class and inter-class constraints simultaneously in the exponential feature projection space. The extensive experiments on the labeled face in the wild (LFW), youtube faces (YTF), and IARPA Janus benchmark A (IJB-A) datasets demonstrate that the proposed methods outperform the mainstream DML methods and approach the state-of-The-Art performance.