UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition
This work addresses the need for efficient and effective face verification in real-world applications, offering an incremental improvement over existing sample-to-sample and sample-to-class methods.
The paper tackles the problem of face recognition by proposing a unified threshold integrated sample-to-sample loss (USS loss) that explicitly separates positive from negative facial pairs, resulting in exceptional performance that outperforms state-of-the-art methods like CosFace and ArcFace on multiple benchmarks.
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.