Abstract
We address the problem of bias in automated face recognition and demographic attribute estimation algorithms, where errors are lower on certain cohorts belonging to specific demographic groups. We present a novel de-biasing adversarial network (DebFace) that learns to extract disentangled feature representations for both unbiased face recognition and demographics estimation. The proposed network consists of one identity classifier and three demographic classifiers (for gender, age, and race) that are trained to distinguish identity and demographic attributes, respectively. Adversarial learning is adopted to minimize correlation among feature factors so as to abate bias influence from other factors. We also design a new scheme to combine demographics with identity features to strengthen robustness of face representation in different demographic groups. The experimental results show that our approach is able to reduce bias in face recognition as well as demographics estimation while achieving state-of-the-art performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This is different from the notion of machine learning bias, defined as “any basis for choosing one generalization [hypothesis] over another, other than strict consistency with the observed training instances” [15].
- 2.
In our case, \(K_G=2\), i.e., male and female.
- 3.
To clarify, we consider two race groups, Black and White; and two ethnicity groups, East Asian and Indian. The word race denotes both race and ethnicity in this paper.
References
Abadi, M., et al.: Deep learning with differential privacy. In: Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, pp. 308–318 (2016)
Amini, A., Soleimany, A., Schwarting, W., Bhatia, S., Rus, D.: Uncovering and mitigating algorithmic bias through learned latent structure. In: AAAI/ACM Conference on AI, Ethics, and Society (2019)
Bolukbasi, T., Chang, K.W., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In: Advances in Neural Information Processing Systems, pp. 4349–4357 (2016)
Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. arXiv preprint arXiv:1906.07413 (2019)
Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: Vggface2: a dataset for recognising faces across pose and age. In: IEEE International Conference on Automatic Face & Gesture Recognition. IEEE (2018)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Chen, B.C., Chen, C.S., Hsu, W.H.: Cross-age reference coding for age-invariant face recognition and retrieval. In: ECCV (2014)
Cheng, J., Li, Y., Wang, J., Yu, L., Wang, S.: Exploiting effective facial patches for robust gender recognition. Tsinghua Sci. Technol. 24(3), 333–345 (2019)
Cook, C.M., Howard, J.J., Sirotin, Y.B., Tipton, J.L., Vemury, A.R.: Demographic effects in facial recognition and their dependence on image acquisition: an evaluation of eleven commercial systems. IEEE Trans. Biometrics Behav. Identity Sci. 1, 32–41 (2019)
Cui, Y., Jia, M., Lin, T.Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: CVPR (2019)
Deb, D., Best-Rowden, L., Jain, A.K.: Face recognition performance under aging. In: CVPRW (2017)
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: CVPR (2019)
Dietterich, T.G., Kong, E.B.: Machine learning bias, statistical bias, and statistical variance of decision tree algorithms. Tech. rep. (1995)
Drummond, C., Holte, R.C., et al.: C4. 5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling. In: Workshop on Learning from Imbalanced Datasets II. Citeseer (2003)
Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: The 22nd ACM SIGSAC (2015)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)
Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87–102. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_6
Han, H., A, K.J., Shan, S., Chen, X.: Heterogeneous face attribute estimation: a deep multi-task learning approach. IEEE Trans. Pattern Anal. Mach. Intelli. PP(99), 1–1 (2017)
Hayat, M., Khan, S., Zamir, W., Shen, J., Shao, L.: Max-margin class imbalanced learning with Gaussian affinity. arXiv preprint arXiv:1901.07711 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Howard, J., Sirotin, Y., Vemury, A.: The effect of broad and specific demographic homogeneity on the imposter distributions and false match rates in face recognition algorithm performance. In: IEEE BTAS (2019)
Huang, C., Li, Y., Chen, C.L., Tang, X.: Deep imbalanced learning for face recognition and attribute prediction. IEEE Trans Pattern Anal. Mach. Intell. (2019)
Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments (2008)
Jourabloo, A., Yin, X., Liu, X.: Attribute preserved face de-identification. In: ICB (2015)
Khan, S., Hayat, M., Zamir, S.W., Shen, J., Shao, L.: Striking the right balance with uncertainty. In: CVPR (2019)
Kim, H., Mnih, A.: Disentangling by factorising. arXiv preprint arXiv:1802.05983 (2018)
Klare, B.F., Burge, M.J., Klontz, J.C., Bruegge, R.W.V., Jain, A.K.: Face recognition performance: Role of demographic information. IEEE Trans. Inform. Forensics Secur. 7(6), 1789–1801 (2012)
Klare, B.F., et al.: Pushing the frontiers of unconstrained face detection and recognition: Iarpa janus benchmark a. In: CVPR (2015)
Liu, F., Zeng, D., Zhao, Q., Liu, X.: Disentangling features in 3D face shapes for joint face reconstruction and recognition. In: CVPR (2018)
Liu, Y., Wang, Z., Jin, H., Wassell, I.: Multi-task adversarial network for disentangled feature learning. In: CVPR (2018)
Liu, Y.H., Chen, Y.T.: Face recognition using total margin-based adaptive fuzzy support vector machines. IEEE Trans. Neural Networks 18(1), 178–192 (2007)
Liu, Y., Wei, F., Shao, J., Sheng, L., Yan, J., Wang, X.: Exploring disentangled feature representation beyond face identification. In: CVPR (2018)
Locatello, F., Bauer, S., Lucic, M., Gelly, S., Schölkopf, B., Bachem, O.: Challenging common assumptions in the unsupervised learning of disentangled representations. arXiv preprint arXiv:1811.12359 (2018)
Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NIPS (2018)
Maze, B., et al.: Iarpa janus benchmark-c: face dataset and protocol. In: 2018 ICB (2018)
Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: AgeDB: the first manually collected, in-the-wild age database. In: CVPRW (2017)
Mullick, S.S., Datta, S., Das, S.: Generative adversarial minority oversampling. arXiv preprint arXiv:1903.09730 (2019)
Narayanaswamy, S., et al.: Learning disentangled representations with semi-supervised deep generative models. In: NIPS (2017)
Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Ordinal regression with multiple output CNN for age estimation. In: CVPR (2016)
Patrick Grother, M.N., Hanaoka, K.: Face recognition vendor test (FRVT) part 3: demographic effects. Tech. rep., National Institute of Standards and Technology (2019)
Rothe, R., Timofte, R., Van Gool, L.: Deep expectation of real and apparent age from a single image without facial landmarks. IJCV 126(2–4), 144–157 (2018)
Schmidhuber, J.: Learning factorial codes by predictability minimization. Neural Comput. 4(6), 863–879 (1992)
Setty, S., et al.: Indian movie face database: a benchmark for face recognition under wide variations. In: NCVPRIPG (2013)
Shi, Y., Jain, A.K., Kalka, N.D.: Probabilistic face embeddings. arXiv preprint arXiv:1904.09658 (2019)
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: Closing the gap to human-level performance in face verification. In: CVPR (2014)
Tao, C., Lv, F., Duan, L., Wu, M.: Minimax entropy network: learning category-invariant features for domain adaptation. arXiv preprint arXiv:1904.09601 (2019)
Torralba, A., Efros, A.A., et al.: Unbiased look at dataset bias. In: CVPR (2011)
Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: CVPR (2017)
Tran, L., Yin, X., Liu, X.: Representation learning by rotating your faces. IEEE Trans. Pattern Anal. Mach. Intell. 41(12), 3007–3021 (2019)
Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: CVPR (2015)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926–930 (2018)
Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. In: CVPR (2018)
Wang, M., Deng, W.: Mitigating bias in face recognition using skewness-aware reinforcement learning. In: CVPR (2020)
Wang, M., Deng, W., Hu, J., Tao, X., Huang, Y.: Racial faces in the wild: reducing racial bias by information maximization adaptation network. In: ICCV (2019)
Wang, P., Su, F., Zhao, Z., Guo, Y., Zhao, Y., Zhuang, B.: Deep class-skewed learning for face recognition. Neurocomputing 363, 35–45 (2019)
Xie, W., Zisserman, A.: Multicolumn networks for face recognition. arXiv preprint arXiv:1807.09192 (2018)
Yin, B., Tran, L., Li, H., Shen, X., Liu, X.: Towards interpretable face recognition. In: ICCV (2019)
Yin, X., Liu, X.: Multi-task convolutional neural network for pose-invariant face recognition. IEEE Trans. Image Process. 27(2), 964–975 (2017)
Yin, X., Yu, X., Sohn, K., Liu, X., Chandraker, M.: Towards large-pose face frontalization in the wild. In: ICCV (2017)
Yin, X., Yu, X., Sohn, K., Liu, X., Chandraker, M.: Feature transfer learning for face recognition with under-represented data. In: CVPR (2019)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Zhang, X., Fang, Z., Wen, Y., Li, Z., Qiao, Y.: Range loss for deep face recognition with long-tailed training data. In: CVPR (2017)
Zhang, Y., Zhou, Z.H.: Cost-sensitive face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(10), 1758–1769 (2009)
Zhang, Z., Song, Y., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: CVPR. IEEE (2017)
Zhang, Z., et al.: Gait recognition via disentangled representation learning. In: CVPR (2019)
Acknowledgement
This work is supported by U.S. Department of Commerce (#60NANB19D154), National Institute of Standards and Technology. The authors thank reviewers, area chairs, Dr. John J. Howard, and Dr. Yevgeniy Sirotin for offering constructive comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Gong, S., Liu, X., Jain, A.K. (2020). Jointly De-Biasing Face Recognition and Demographic Attribute Estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12374. Springer, Cham. https://doi.org/10.1007/978-3-030-58526-6_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-58526-6_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58525-9
Online ISBN: 978-3-030-58526-6
eBook Packages: Computer ScienceComputer Science (R0)