Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Unsupervised and Semi-supervised Bias Benchmarking in Face Recognition

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13673))

Included in the following conference series:

Abstract

We introduce Semi-supervised Performance Evaluation for Face Recognition (SPE-FR). SPE-FR is a statistical method for evaluating the performance and algorithmic bias of face verification systems when identity labels are unavailable or incomplete. The method is based on parametric Bayesian modeling of the face embedding similarity scores. SPE-FR produces point estimates, performance curves, and confidence bands that reflect uncertainty in the estimation procedure. Focusing on the unsupervised setting wherein no identity labels are available, we validate our method through experiments on a wide range of face embedding models and two publicly available evaluation datasets. Experiments show that SPE-FR can accurately assess performance on data with no identity labels, and confidently reveal demographic biases in system performance.

A. Chouldechova and W. Xia—Work done when at Amazon.

A. Chouldechova and S. Deng—Equal contribution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Some have developed methods for estimating group fairness metrics in the presence of noisy or inferred group membership labels [4, 9, 10, 44]. Understanding how SPE-FR performs with respect to the true unknown groups using inferred group information is an interesting and important question, but beyond the scope of the present work.

  2. 2.

    BUPT-BalancedFace does not provide gender annotations, we generated pseudo labels from open-source face analysis repository Insightface [3, 13,14,15,16, 25, 26].

References

  1. Albiero, V., KS, K., Vangara, K., Zhang, K., King, M.C., Bowyer, K.W.: Analysis of gender inequality in face recognition accuracy. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, pp. 81–89 (2020)

    Google Scholar 

  2. Albright, T.D.: Why eyewitnesses fail. Proc. Natl. Acad. Sci. 114(30), 7758–7764 (2017)

    Article  Google Scholar 

  3. An, X., et al: Partial fc: training 10 million identities on a single machine. In: Arxiv 2010.05222 (2020)

    Google Scholar 

  4. Awasthi, P., Beutel, A., Kleindessner, M., Morgenstern, J., Wang, X.: Evaluating fairness of machine learning models under uncertain and incomplete information. In: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pp. 206–214 (2021)

    Google Scholar 

  5. Balakrishnan, G., Xiong, Y., Xia, W., Perona, P.: Towards causal benchmarking of bias in face analysis algorithms. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 547–563. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58523-5_32

    Chapter  Google Scholar 

  6. Beery, S., Van Horn, G., Perona, P.: Recognition in terra incognita. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 472–489. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_28

    Chapter  Google Scholar 

  7. ter Braak, C.J., Vrugt, J.A.: Differential evolution Markov chain with snooker updater and fewer chains. Stat. Comput. 18(4), 435–446 (2008)

    Article  MathSciNet  Google Scholar 

  8. Buolamwini, J., Gebru, T.: Gender shades: intersectional accuracy disparities in commercial gender classification. In: Conference on Fairness, Accountability and Transparency, pp. 77–91. PMLR (2018)

    Google Scholar 

  9. Chen, J., Kallus, N., Mao, X., Svacha, G., Udell, M.: Fairness under unawareness: assessing disparity when protected class is unobserved. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, pp. 339–348 (2019)

    Google Scholar 

  10. Coston, A., et al.: Fair transfer learning with missing protected attributes. In: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pp. 91–98 (2019)

    Google Scholar 

  11. Deepglint: https://trillionpairs.deepglint.com/overview. https://trillionpairs.deepglint.com/overview

  12. Deng, J., Guo, J., Liu, T., Gong, M., Zafeiriou, S.: Sub-center arcface: Boosting face recognition by large-scale noisy web faces. In: European Conference on Computer Vision, pp. 741–757. Springer (2020)

    Google Scholar 

  13. Deng, J., Guo, J., Liu, T., Gong, M., Zafeiriou, S.: Sub-center ArcFace: boosting face recognition by large-scale noisy web faces. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 741–757. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_43

    Chapter  Google Scholar 

  14. Deng, J., Guo, J., Niannan, X., Zafeiriou, S.: Arcface: Additive angular margin loss for deep face recognition. In: CVPR (2019)

    Google Scholar 

  15. Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: Retinaface: single-shot multi-level face localisation in the wild. In: CVPR (2020)

    Google Scholar 

  16. Deng, J., et al.: The menpo benchmark for multi-pose 2d and 3d facial landmark localisation and tracking. IJCV (2018)

    Google Scholar 

  17. Deng, S., Xiong, Y., Wang, M., Xia, W., Soatto, S.: Harnessing unrecognizable faces for improving face recognition. arXiv preprint arXiv:2106.04112 (2021)

  18. Deng, W., Zheng, L.: Are labels always necessary for classifier accuracy evaluation? In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15069–15078 (2021)

    Google Scholar 

  19. Fechner, G.T.: Kollektivmasslehre. Engelmann (1897)

    Google Scholar 

  20. Fernández, C., Steel, M.F.: On bayesian modeling of fat tails and skewness. J. Am. Stat. Assoc. 93(441), 359–371 (1998)

    MathSciNet  MATH  Google Scholar 

  21. Garg, S., Balakrishnan, S., Lipton, Z.C., Neyshabur, B., Sedghi, H.: Leveraging unlabeled data to predict out-of-distribution performance. arXiv preprint arXiv:2201.04234 (2022)

  22. GoogleAI: Responsible ai practices. https://ai.google/responsibilities/responsible-ai-practices/

  23. Grother, P.J., Ngan, M.L., Hanaoka, K.K., et al.: Face recognition vendor test part 3: demographic effects (2019)

    Google Scholar 

  24. Guillory, D., Shankar, V., Ebrahimi, S., Darrell, T., Schmidt, L.: Predicting with confidence on unseen distributions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1134–1144 (2021)

    Google Scholar 

  25. Guo, J., Deng, J., Lattas, A., Zafeiriou, S.: Sample and computation redistribution for efficient face detection. arXiv preprint arXiv:2105.04714 (2021)

  26. Guo, J., Deng, J., Xue, N., Zafeiriou, S.: Stacked dense u-nets with dual transformers for robust face alignment. In: BMVC (2018)

    Google Scholar 

  27. Hartig, F., Minunno, F., Paul, S.: BayesianTools: general-purpose MCMC and SMC samplers and tools for bayesian statistics (2019). https://CRAN.R-project.org/package=BayesianTools, r package version 0.1.7

  28. Hashimoto, T., Srivastava, M., Namkoong, H., Liang, P.: Fairness without demographics in repeated loss minimization. In: International Conference on Machine Learning,pp. 1929–1938. PMLR (2018)

    Google Scholar 

  29. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Coference on Computer Vision and Pattern Recognition,pp. 770–778 (2016)

    Google Scholar 

  30. He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38

    Chapter  Google Scholar 

  31. IBM: Trustworthy ai.https://www.ibm.com/watson/trustworthy-ai

  32. Ji, D., Smyth, P., Steyvers, M.: Can i trust my fairness metric? assessing fairness with unlabeled data and bayesian inference. arXiv preprint arXiv:2010.09851 (2020)

  33. Kearns, M., Roth, A.: The ethical algorithm: The science of socially aware algorithm design. Oxford University Press (2019)

    Google Scholar 

  34. Keles, U., Lin, C., Adolphs, R.: A cautionary note on predicting social judgments from faces with deep neural networks. Affective Sci. 2(4), 438–454 (2021)

    Article  Google Scholar 

  35. Kortylewski, A., Egger, B., Schneider, A., Gerig, T., Morel-Forster, A., Vetter, T.: Analyzing and reducing the damage of dataset bias to face recognition with synthetic data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,pp. 0 (2019)

    Google Scholar 

  36. Krishnapriya, K., Albiero, V., Vangara, K., King, M.C., Bowyer, K.W.: Issues related to face recognition accuracy varying based on race and skin tone. IEEE Trans. Technol. Soc. 1(1), 8–20 (2020)

    Article  Google Scholar 

  37. Krivosheev, E., Bykau, S., Casati, F., Prabhakar, S.: Detecting and preventing confused labels in crowdsourced data. Proc. VLDB Endowment 13(12), 2522–2535 (2020)

    Article  Google Scholar 

  38. Lahoti, P., et al.: Fairness without demographics through adversarially reweighted learning. arXiv preprint arXiv:2006.13114 (2020)

  39. Maze, B., et al.: Iarpa janus benchmark-c: Face dataset and protocol. In: 2018 International Conference on Biometrics (ICB), pp. 158–165. IEEE (2018)

    Google Scholar 

  40. McKone, E., Dawel, A., Robbins, R.A., Shou, Y., Chen, N., Crookes, K.: Why the other-race effect matters: poor recognition of other-race faces impacts everyday social interactions. British J. Psychol. (2021)

    Google Scholar 

  41. Muthén, B., Shedden, K.: Finite mixture modeling with mixture outcomes using the em algorithm. Biometrics 55(2), 463–469 (1999)

    Article  MATH  Google Scholar 

  42. Phillips, P.J., Yates, A.N., Hu, Y., Hahn, C.A., Noyes, E., Jackson, K., Cavazos, J.G., Jeckeln, G., Ranjan, R., Sankaranarayanan, S., et al.: Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms. Proc. Natl. Acad. Sci. 115(24), 6171–6176 (2018)

    Article  Google Scholar 

  43. PricewaterhouseCoopers: Responsible ai toolkit. https://www.pwc.com/gx/en/issues/data-and-analytics/artificial-intelligence/what-is-responsible-ai.html

  44. Prost, F., et al.: Measuring model fairness under noisy covariates: a theoretical perspective. In: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp. 873–883 (2021)

    Google Scholar 

  45. Raji, I.D., Gebru, T., Mitchell, M., Buolamwini, J., Lee, J., Denton, E.: Saving face: Investigating the ethical concerns of facial recognition auditing. In: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pp. 145–151 (2020)

    Google Scholar 

  46. Ranjan, R., Castillo, C.D., Chellappa, R.: L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507 (2017)

  47. Ricanek, K., Tesafaye, T.: Morph: A longitudinal image database of normal adult age-progression. In: 7th International Conference on Automatic Face and Gesture Recognition (FGR06), pp. 341–345. IEEE (2006)

    Google Scholar 

  48. Robinson, J.P., Livitz, G., Henon, Y., Qin, C., Fu, Y., Timoner, S.: Face recognition: too bias, or not too bias? In: Proceedings of the ieee/cvf Conference on Computer Vision and Pattern Recognition Workshops, p. 1 (2020)

    Google Scholar 

  49. Rubio, F., Steel, M.: The family of two-piece distributions. Significance 17, 12–13 (2020). https://doi.org/10.1111/j.1740-9713.2020.01352.x

  50. Rubio, F.J., Ogundimu, E.O., Hutton, J.L.: On modelling asymmetric data using two-piece sinh-arcsinh distributions. Brazilian J. Probability Stat., 485–501 (2016)

    Google Scholar 

  51. Srinivas, N., Ricanek, K., Michalski, D., Bolme, D.S., King, M.: Face recognition algorithm bias: performance differences on images of children and adults. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)

    Google Scholar 

  52. Tanaka, J.W., Kiefer, M., Bukach, C.M.: A holistic account of the own-race effect in face recognition: Evidence from a cross-cultural study. Cognition 93(1), B1–B9 (2004)

    Article  Google Scholar 

  53. Vangara, K., King, M.C., Albiero, V., Bowyer, K., et al.: Characterizing the variability in face recognition accuracy relative to race. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 0 (2019)

    Google Scholar 

  54. Vorvoreanu, M., Walker, K.: Advancing ai trustworthiness: Updates on responsible ai research, February 2022. https://www.microsoft.com/en-us/research/blog/advancing-ai-trustworthiness-updates-on-responsible-ai-research/

  55. Wang, F., et al.: The devil of face recognition is in the noise. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 780–795. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_47

    Chapter  Google Scholar 

  56. Wang, H., et al.: Cosface: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5265–5274 (2018)

    Google Scholar 

  57. Wang, M., Deng, W., Hu, J., Tao, X., Huang, Y.: Racial faces in the wild: Reducing racial bias by information maximization adaptation network. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 692–702 (2019)

    Google Scholar 

  58. Wang, M., Zhang, Y., Deng, W.: Meta balanced network for fair face recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2021)

    Google Scholar 

  59. Wang, Z., et al.: Towards fairness in visual recognition: effective strategies for bias mitigation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8919–8928 (2020)

    Google Scholar 

  60. Welinder, P., Welling, M., Perona, P.: A lazy man’s approach to benchmarking: Semisupervised classifier evaluation and recalibration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3262–3269 (2013)

    Google Scholar 

  61. Zhou, K., Liu, Z., Qiao, Y., Xiang, T., Loy, C.C.: Domain generalization in vision: a survey. arXiv preprint arXiv:2103.02503 (2021)

Download references

Author information

Authors and Affiliations

  1. AWS AI Labs, Seattle, USA

    Alexandra Chouldechova, Siqi Deng, Yongxin Wang, Wei Xia & Pietro Perona

Authors
  1. Alexandra Chouldechova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Siqi Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yongxin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wei Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Pietro Perona
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Siqi Deng .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2822 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chouldechova, A., Deng, S., Wang, Y., Xia, W., Perona, P. (2022). Unsupervised and Semi-supervised Bias Benchmarking in Face Recognition. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13673. Springer, Cham. https://doi.org/10.1007/978-3-031-19778-9_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19778-9_17

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19777-2

  • Online ISBN: 978-3-031-19778-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation