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

arXiv: https://arxiv.org/abs/2311.02523 · HTML: https://mlsanity.com/paper/2311.02523/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 4 Nov 2023.

## Builds on (most cited first, 19 of 19)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Learning towards Minimum Hyperspherical Energy](https://mlsanity.com/paper/1805.09298/) (2018)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [Masked Face Recognition Challenge: The InsightFace Track Report](https://mlsanity.com/paper/2108.08191/) (2021)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition](https://mlsanity.com/paper/2203.11593/) (2022)

## Built on by (most cited first, 10 of 10)

- [50 Years of Automated Face Recognition](https://mlsanity.com/paper/2505.24247/) (2025)
- [LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition](https://mlsanity.com/paper/2403.08161/) (2024)
- [LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition](https://mlsanity.com/paper/2501.13420/) (2025)
- [IDFace: Face Template Protection for Efficient and Secure Identification](https://mlsanity.com/paper/2507.12050/) (2025)
- [EPL: Empirical Prototype Learning for Deep Face Recognition](https://mlsanity.com/paper/2405.12447/) (2024)
- [Non-Adaptive Adversarial Face Generation](https://mlsanity.com/paper/2507.12107/) (2025)
- [QCFace: Image Quality Control for boosting Face Representation & Recognition](https://mlsanity.com/paper/2510.15289/) (2025)
- [SymFace: Additional Facial Symmetry Loss for Deep Face Recognition](https://mlsanity.com/paper/2409.11816/) (2024)
- [AdapNet: Adaptive Noise-Based Network for Low-Quality Image Retrieval](https://mlsanity.com/paper/2405.17718/) (2024)
- [EventFace: Event-Based Face Recognition via Structure-Driven Spatiotemporal Modeling](https://mlsanity.com/paper/2604.06782/) (2026)

## Abstract (arXiv)

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.