Deep face recognition has achieved great success due to large-scale training databases and rapidly developing loss functions. The existing algorithms devote to realizing an ideal idea: minimizing the intra-class distance and maximizing the inter-class distance. However, they may neglect that there are also low quality training images which should not be optimized in this strict way. Considering the imperfection of training databases, we propose that intra-class and inter-class objectives can be optimized in a moderate way to mitigate overfitting problem, and further propose a novel loss function, named sigmoid-constrained hypersphere loss (SFace). Specifically, SFace imposes intra-class and inter-class constraints on a hypersphere manifold, which are controlled by two sigmoid gradient re-scale functions respectively. The sigmoid curves precisely re-scale the intra-class and inter-class gradients so that training samples can be optimized to some degree. Therefore, SFace can make a better balance between decreasing the intra-class distances for clean examples and preventing overfitting to the label noise, and contributes more robust deep face recognition models. Extensive experiments of models trained on CASIA-WebFace, VGGFace2, and MS-Celeb-1M databases, and evaluated on several face recognition benchmarks, such as LFW, MegaFace and IJB-C databases, have demonstrated the superiority of SFace.

中文翻译：

---

SFace：Sigmoid约束的超球面损失以实现可靠的人脸识别

由于大规模的培训数据库和迅速发展的损失功能，深层人脸识别已取得了巨大的成功。现有的算法致力于实现理想的想法：最小化类内距离并最大化类间距离。但是，他们可能会忽略还有质量低下的训练图像，不应以这种严格的方式对其进行优化。考虑到训练数据库的不完善性，我们提出可以适当地优化类内和类间目标以减轻过度拟合问题，并进一步提出一种新的损失函数，称为S形约束超球面损失（SFace）。具体地说，SFace在超球面流形上施加类内和类间约束，分别由两个S型梯度重新缩放函数控制。S形曲线精确地重新缩放了类别内和类别间的梯度，因此可以在某种程度上优化训练样本。因此，SFace可以在减少用于干净示例的类内距离与防止标签噪声过度拟合之间取得更好的平衡，并有助于建立更可靠的深层人脸识别模型。在CASIA-WebFace，VGGFace2和MS-Celeb-1M数据库上训练并在多个人脸识别基准（例如LFW，MegaFace和IJB-C数据库）上进行了评估的模型的大量实验证明了SFace的优越性。并贡献了更强大的深脸识别模型。在CASIA-WebFace，VGGFace2和MS-Celeb-1M数据库上训练并在多个面部识别基准（例如LFW，MegaFace和IJB-C数据库）上进行了评估的模型的大量实验证明了SFace的优越性。并贡献了更强大的深脸识别模型。在CASIA-WebFace，VGGFace2和MS-Celeb-1M数据库上训练并在多个面部识别基准（例如LFW，MegaFace和IJB-C数据库）上进行了评估的模型的大量实验证明了SFace的优越性。