UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

• DOI: 10.48550/arxiv.2311.02523
• Publication Date: 2023-01-01
• Authors: Li, Qiufu; Jia, Xi; Zhou, Jiancan; Shen, Linlin; Duan, Jinming
• Keywords: FOS: Computer and information sciences; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; Computer Science - Human-Computer Interaction; Human-Computer Interaction (cs.HC)

Accepted by Neurips 2023<br/>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.<br/>