Full search page →

ArcFace (Deng et al., CVPR 2019; TPAMI 2022)

Optional · paper guide 1 of 3 for DLCV 02A · Face Recognition and Metric Learning. Citation numbers refer to the reference list at the bottom of this page.

Navigate: this page and this track: Navigate: this page and this track

On this page

Supplementary notes · 6

  1. Aligning a face: the least-squares similarity transform
  2. How large must the scale s be?
  3. Margin losses side by side: one formula and its edge cases
  4. Beyond one center per class: sub-centers, quality-aware margins and Partial FC
  5. Measuring very small error rates
  6. Before deep learning: eigenfaces and Fisherfaces

Paper guides · 3

  1. ArcFace (Deng et al., CVPR 2019; TPAMI 2022)
  2. NIST FRVT Part 3: Demographic Effects (Grother, Ngan and Hanaoka, 2019)
  3. Guide to the Modern view surveys

Deep Learning for Computer Vision

  1. 02 · Deep Image Classification
View the whole course tree →

Challenge

By 2018 several losses added margins to the softmax (SphereFace, CosFace), with different geometric meanings and training difficulties. The authors wanted a margin with a clear geometric interpretation that is also easy to train at scale [15].

Normalized features and class weights produce an angle; the target-class angular margin changes the training logit before rescaling and cross-entropy.
Original paper figure 2 — Normalized features and class weights produce an angle; the target-class angular margin changes the training logit before rescaling and cross-entropy.

Figure source: [15], Published paper PDF, PDF page 3. Original PDF.

Method

Normalize features and class weights, rescale by ss, and add an angular margin mm to the angle between a feature and its own class center: the target logit becomes scos⁡(θ+m)s\cos(\theta + m). Because the margin is added to the angle, it equals a geodesic distance on the hypersphere [15]. The journal version [16] extends the work with sub-center ArcFace for noisy web data, a combined-margin analysis that places SphereFace, CosFace and ArcFace in one formula, and further experiments (including inverting the model to synthesize faces).

Results

The experiments compare losses with the backbone and training data held fixed, written as [training set, network, loss] [16]. Read the tables in that spirit: compare rows that differ only in the loss; a change of training set (for example a cleaned versus a raw web set) moves results by more than many loss changes. The main test sets are LFW and similar pair-based sets, MegaFace, and IJB-B/IJB-C; for IJB the reported number is TAR at FAR = 10−410^{-4} on template pairs, where a template’s embedding is the mean of its images’ embeddings [16]. The experimental setup (five RetinaFace landmarks, 112×112112 \times 112 crops, 512-D embeddings, s=64s = 64, m=0.5m = 0.5) is documented in the paper [16] and has become a common default.

Problems

The gains on LFW are tiny because LFW is saturated; the informative comparisons are at low FAR on IJB-B/C and on large galleries. Several training sets used in this line of work have since been withdrawn or changed [30], which makes exact reproduction difficult. The margin assumes labels are correct; with heavy label noise the plain loss suffers, which is what sub-centers address.

Conclusion

ArcFace is the reference form of the margin-based softmax in this chapter, and its geometric argument (constant geodesic margin) is the one Figure 2 illustrates.

References

  1. M. Wang and W. Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, pp. 215–244, 2021. doi
  2. P. Grother, M. Ngan and K. Hanaoka, “Face Recognition Vendor Test (FRVT) Part 3: Demographic Effects,” NIST Interagency Report 8280, National Institute of Standards and Technology, 2019. doi
  3. National Institute of Standards and Technology, “Face Recognition Technology Evaluation (FRTE) 1:1 Verification,” evaluation web page, accessed 2026. NIST
  4. K. Zhang, Z. Zhang, Z. Li and Y. Qiao, “Joint face detection and alignment using multitask cascaded convolutional networks,” IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499–1503, 2016. doi
  5. J. Deng, J. Guo, E. Ververas, I. Kotsia and S. Zafeiriou, “RetinaFace: Single-shot multi-level face localisation in the wild,” in Proc. IEEE/CVF CVPR, 2020. CVF
  6. Y. Taigman, M. Yang, M. Ranzato and L. Wolf, “DeepFace: Closing the gap to human-level performance in face verification,” in Proc. IEEE CVPR, 2014. CVF
  7. F. Schroff, D. Kalenichenko and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering,” in Proc. IEEE CVPR, 2015. CVF
  8. S. Chopra, R. Hadsell and Y. LeCun, “Learning a similarity metric discriminatively, with application to face verification,” in Proc. IEEE CVPR, vol. 1, pp. 539–546, 2005. doi
  9. R. Hadsell, S. Chopra and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in Proc. IEEE CVPR, vol. 2, pp. 1735–1742, 2006. doi
  10. A. Hermans, L. Beyer and B. Leibe, “In defense of the triplet loss for person re-identification,” arXiv:1703.07737, 2017. arXiv
  11. F. Wang, X. Xiang, J. Cheng and A. L. Yuille, “NormFace: L2 hypersphere embedding for face verification,” in Proc. ACM International Conference on Multimedia, pp. 1041–1049, 2017. doi
  12. W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj and L. Song, “SphereFace: Deep hypersphere embedding for face recognition,” in Proc. IEEE CVPR, 2017. CVF
  13. H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li and W. Liu, “CosFace: Large margin cosine loss for deep face recognition,” in Proc. IEEE/CVF CVPR, 2018. CVF
  14. F. Wang, J. Cheng, W. Liu and H. Liu, “Additive margin softmax for face verification,” IEEE Signal Processing Letters, vol. 25, no. 7, pp. 926–930, 2018. doi
  15. J. Deng, J. Guo, N. Xue and S. Zafeiriou, “ArcFace: Additive angular margin loss for deep face recognition,” in Proc. IEEE/CVF CVPR, 2019. CVF
  16. J. Deng, J. Guo, J. Yang, N. Xue, I. Kotsia and S. Zafeiriou, “ArcFace: Additive angular margin loss for deep face recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 10, pp. 5962–5979, 2022. doi
  17. Y. Wen, K. Zhang, Z. Li and Y. Qiao, “A discriminative feature learning approach for deep face recognition,” in Proc. ECCV, pp. 499–515, 2016. doi
  18. J. Deng, J. Guo, T. Liu, M. Gong and S. Zafeiriou, “Sub-center ArcFace: Boosting face recognition by large-scale noisy web faces,” in Proc. ECCV, pp. 741–757, 2020. doi
  19. Q. Meng, S. Zhao, Z. Huang and F. Zhou, “MagFace: A universal representation for face recognition and quality assessment,” in Proc. IEEE/CVF CVPR, 2021. CVF
  20. M. Kim, A. K. Jain and X. Liu, “AdaFace: Quality adaptive margin for face recognition,” in Proc. IEEE/CVF CVPR, 2022. CVF
  21. X. An, J. Deng, J. Guo, Z. Feng, X. Zhu, J. Yang and T. Liu, “Killing two birds with one stone: Efficient and robust training of face recognition CNNs by Partial FC,” in Proc. IEEE/CVF CVPR, 2022. CVF
  22. A. Martin, G. Doddington, T. Kamm, M. Ordowski and M. Przybocki, “The DET curve in assessment of detection task performance,” in Proc. Eurospeech, pp. 1895–1898, 1997. ISCA
  23. G. B. Huang, M. Mattar, T. Berg and E. Learned-Miller, “Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments,” in Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition, Marseille, 2008. HAL
  24. I. Kemelmacher-Shlizerman, S. M. Seitz, D. Miller and E. Brossard, “The MegaFace benchmark: 1 million faces for recognition at scale,” in Proc. IEEE CVPR, 2016. CVF
  25. University of Washington, “MegaFace and MF2: Million-scale face recognition,” project web page, accessed 2026. project page
  26. Y. Guo, L. Zhang, Y. Hu, X. He and J. Gao, “MS-Celeb-1M: A dataset and benchmark for large-scale face recognition,” in Proc. ECCV, pp. 87–102, 2016. doi
  27. C. Whitelam, E. Taborsky, A. Blanton, B. Maze, J. Adams, T. Miller, N. Kalka, A. K. Jain, J. A. Duncan, K. Allen, J. Cheney and P. Grother, “IARPA Janus Benchmark-B face dataset,” in Proc. IEEE CVPR Workshops, 2017. CVF
  28. B. Maze, J. Adams, J. A. Duncan, N. Kalka, T. Miller, C. Otto, A. K. Jain, W. T. Niggel, J. Anderson, J. Cheney and P. Grother, “IARPA Janus Benchmark – C: Face dataset and protocol,” in Proc. International Conference on Biometrics (ICB), pp. 158–165, 2018. doi
  29. Z. Zhu, G. Huang, J. Deng, Y. Ye, J. Huang, X. Chen, J. Zhu, T. Yang, J. Lu, D. Du and J. Zhou, “WebFace260M: A benchmark unveiling the power of million-scale deep face recognition,” in Proc. IEEE/CVF CVPR, 2021. CVF
  30. K. Peng, A. Mathur and A. Narayanan, “Mitigating dataset harms requires stewardship: Lessons from 1000 papers,” in Proc. NeurIPS Datasets and Benchmarks Track, 2021. proceedings
  31. G. Bae, M. de La Gorce, T. Baltrušaitis, C. Hewitt, D. Chen, J. Valentin, R. Cipolla and J. Shen, “DigiFace-1M: 1 million digital face images for face recognition,” in Proc. IEEE/CVF WACV, 2023. CVF
  32. M. Kim, F. Liu, A. Jain and X. Liu, “DCFace: Synthetic face generation with dual condition diffusion model,” in Proc. IEEE/CVF CVPR, 2023. CVF
  33. F. Boutros, V. Struc, J. Fierrez and N. Damer, “Synthetic data for face recognition: Current state and future prospects,” Image and Vision Computing, vol. 135, art. 104688, 2023. doi
  34. M. Wang, W. Deng, J. Hu, X. Tao and Y. Huang, “Racial Faces in the Wild: Reducing racial bias by information maximization adaptation network,” in Proc. IEEE/CVF ICCV, pp. 692–702, 2019. doi
  35. J. Buolamwini and T. Gebru, “Gender Shades: Intersectional accuracy disparities in commercial gender classification,” in Proc. Conference on Fairness, Accountability and Transparency, PMLR 81, pp. 77–91, 2018. PMLR
  36. P. Drozdowski, C. Rathgeb, A. Dantcheva, N. Damer and C. Busch, “Demographic bias in biometrics: A survey on an emerging challenge,” IEEE Transactions on Technology and Society, vol. 1, no. 2, pp. 89–103, 2020. doi
  37. Z. Yu, Y. Qin, X. Li, C. Zhao, Z. Lei and G. Zhao, “Deep learning for face anti-spoofing: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, pp. 5609–5631, 2023. doi
  38. European Commission, “What personal data is considered sensitive?,” data protection guidance referring to Article 9 of the GDPR, accessed 2026. European Commission
  39. European Commission, “AI Act” (Regulation (EU) 2024/1689), policy page, accessed 2026. European Commission
  40. M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 1991. doi
  41. P. N. Belhumeur, J. P. Hespanha and D. J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711–720, 1997. doi