Full search page →

NIST FRVT Part 3: Demographic Effects (Grother, Ngan and Hanaoka, 2019)

Optional · paper guide 2 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

Public claims about bias in face recognition were often based on small studies, on different tasks (such as gender classification), or on a single error type. NIST set out to quantify demographic differentials of contemporary algorithms on large operational datasets [2].

Teaching protocol diagram — split genuine and impostor comparisons, apply the stated threshold and report errors for defined groups. The diagram is not a reproduction of a NIST result plot.
Teaching protocol diagram — split genuine and impostor comparisons, apply the stated threshold and report errors for defined groups. The diagram is not a reproduction of a NIST result plot.

Method

Run many submitted one-to-one and one-to-many algorithms on four large U.S. government image collections with sex, age and race or country-of-birth metadata, and report false positive and false negative rates per group at fixed thresholds [2].

Results

The executive summary’s main result is that false positive differentials were much larger than false negative ones, often by factors of 10 to beyond 100 across groups, and that the size and even the direction of effects depended on the algorithm and the dataset; image quality explained several false negative differences; and some accurate one-to-many algorithms showed undetectable false positive differentials [2].

Reading the evidence

Always check three things for any number you quote: which error (FMR or FNMR, FPIR or FNIR), at which threshold, and on which dataset. The report gives results per algorithm in extensive annexes, so “face recognition is biased by X” is not a statement the report supports; “algorithm A on dataset D at threshold t has false match rates that differ by X between groups” is. The datasets are not public, so results cannot be reproduced outside NIST, and the algorithms were prototypes submitted at the time, not necessarily deployed products [2].

Problems

Country of birth is used as a proxy for race in three of the four datasets [2]; the report measures differentials but does not decide which differences are acceptable; and algorithms have changed since 2019, so current per-algorithm results should be taken from NIST’s ongoing evaluations [3].

Conclusion

It is the basis for the fairness section’s main claims and for the advice to report both error types per group at the operating threshold.

Keep the operating point explicit

For one-to-one verification, suppose larger similarity score SS means a stronger match and acceptance occurs when S≥tS\ge t. For the report’s defined comparison stratum gg,

FMR⁡g(t)=Pr⁡(S≥t∣different identities,g),FNMR⁡g(t)=Pr⁡(S<t∣same identity,g).\operatorname{FMR}_g(t)=\Pr(S\ge t\mid\text{different identities},g),\qquad \operatorname{FNMR}_g(t)=\Pr(S<t\mid\text{same identity},g).

tt is the threshold; gg must specify how the pair/population is grouped. A cross-group pair and a same-group pair need not be the same stratum. Both errors depend on the threshold and the image population. Changing to a separate threshold for every group answers a different operating-policy question from comparing groups at one common threshold. Neither rate is itself a complete definition of fairness [2].

One-to-many search additionally depends on the gallery and search decision, so its FPIR/FNIR cannot simply be substituted for the two verification rates. Read uncertainty and small comparison counts alongside an observed differential; an undetected difference is not proof that all populations and capture conditions behave identically [2], [3].

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