State-of-the-art face recognition methods typically take the multi-classification pipeline and adopt the softmax-based loss for optimization. Although these methods have achieved great success, the softmax-based loss has its limitation from the perspective of open set classification: the multi-classification objective in the training phase does not strictly match the objective of open set classification testing. In this paper, we derive a new loss named global boundary CosFace (GB-CosFace). Our GB-CosFace introduces an adaptive global boundary to determine whether two face samples belong to the same identity so that the optimization objective is aligned with the testing process from the perspective of open set classification. Meanwhile, since the loss formulation is derived from the softmax-based loss, our GB-CosFace retains the excellent properties of the softmax-based loss, and CosFace is proved to be a special case of the proposed loss. We analyze and explain the proposed GB-CosFace geometrically. Comprehensive experiments on multiple face recognition benchmarks indicate that the proposed GB-CosFace outperforms current state-of-the-art face recognition losses in mainstream face recognition tasks. Compared to CosFace, our GB-CosFace improves 1.58%, 0.57%, and 0.28% at TAR@FAR=1e-6, 1e-5, 1e-4 on IJB-C benchmark.

翻译：当前最先进的人脸识别方法通常采用多分类流程并选用基于Softmax的损失函数进行优化。尽管这些方法取得了巨大成功，但从开放集分类视角来看，基于Softmax的损失函数存在局限性：训练阶段的多分类目标与开放集分类测试目标并不严格匹配。本文提出了一种名为全局边界CosFace（GB-CosFace）的新损失函数。所提出的GB-CosFace引入自适应全局边界，以判定两个面部样本是否属于同一身份，从而使优化目标与开放集分类视角下的测试过程对齐。同时，由于该损失公式源于基于Softmax的损失函数，GB-CosFace保留了基于Softmax损失函数的优良特性，并且CosFace被证明是所提出损失函数的一个特例。我们从几何角度对GB-CosFace进行了分析与阐释。在多个面部识别基准上的综合实验表明，所提出的GB-CosFace在主流入脸识别任务中优于当前最先进的人脸识别损失函数。与CosFace相比，我们的GB-CosFace在IJB-C基准上，当TAR@FAR=1e-6、1e-5、1e-4时分别提升了1.58%、0.57%和0.28%。