Class-Balanced Training for Deep Face Recognition
Yaobin Zhang, Weihong Deng
Abstract
The performance of deep face recognition depends heavily on the training data. Recently, larger and larger datasets have been developed for the training of deep models. However, most face recognition training sets suffer from the class imbalance problem, and most studies ignore the benefit of optimizing dataset structures. In this paper, we study how class-balanced training can promote face recognition performance. A medium-scale face recognition training set BUPT-CBFace is built by exploring the optimal data structure from massive data. This publicly available dataset is characterized by the uniformly distributed sample size per class, as well as the balance between the number of classes and the number of samples in one class. Experimental results show that deep models trained with BUPT-CBFace can not only achieve comparable results to larger-scale datasets such as MS-Celeb-1M but also alleviate the problem of recognition bias.