SphereFace2: Binary Classification is All You Need for Deep Face Recognition
This addresses limitations in deep face recognition for applications like security and identification, offering a novel training approach that improves empirical performance.
The paper tackles the discrepancy between training and evaluation in softmax-based deep face recognition by proposing SphereFace2, a binary classification framework that circumvents softmax normalization and closed-set assumptions, resulting in consistent outperformance of state-of-the-art methods on popular benchmarks.
State-of-the-art deep face recognition methods are mostly trained with a softmax-based multi-class classification framework. Despite being popular and effective, these methods still have a few shortcomings that limit empirical performance. In this paper, we start by identifying the discrepancy between training and evaluation in the existing multi-class classification framework and then discuss the potential limitations caused by the "competitive" nature of softmax normalization. Motivated by these limitations, we propose a novel binary classification training framework, termed SphereFace2. In contrast to existing methods, SphereFace2 circumvents the softmax normalization, as well as the corresponding closed-set assumption. This effectively bridges the gap between training and evaluation, enabling the representations to be improved individually by each binary classification task. Besides designing a specific well-performing loss function, we summarize a few general principles for this "one-vs-all" binary classification framework so that it can outperform current competitive methods. Our experiments on popular benchmarks demonstrate that SphereFace2 can consistently outperform state-of-the-art deep face recognition methods. The code has been made publicly available.