UniTSFace：用于人脸识别的统一阈值集成样本间损失
UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition
AI总结：
针对现有人脸识别方法的缺陷，提出带明确统一阈值的USS样本间损失，推导相关损失并结合样本-类别损失训练UniTSFace模型，在多基准数据集上性能优于当前最优方法。
摘要：
基于样本-类别的人脸识别模型无法充分挖掘海量人脸图像间的跨样本关系，而基于样本-样本的模型则需要复杂的配对过程才能完成训练。此外，这两种方法都无法满足现实世界人脸验证应用的需求——这类应用需要一个统一阈值来区分正脸对和负脸对。本文提出了一种统一阈值集成的基于样本-样本的损失（USS损失），该损失具备一个明确的统一阈值用于区分正负样本对。受USS损失启发，我们还推导了基于样本-样本的softmax损失和BCE损失，并探讨了它们之间的关系。在MFR、IJB-C、LFW、CFP-FP、AgeDB和MegaFace等多个基准数据集上的广泛评估表明，所提出的USS损失效率极高，且能与基于样本-类别的损失无缝配合。这种嵌入式损失（USS损失与样本-类别Softmax损失）克服了现有方法的缺陷，训练得到的人脸模型UniTSFace表现出卓越性能，优于CosFace、ArcFace、VPL、AnchorFace和UNPG等当前最优方法。我们的代码已公开。
英文摘要：
Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
