Abstract
Significant advancements have been achieved in the domain of face generation with the adoption of diffusion models. However, diffusion models tend to amplify biases during the generative process, resulting in an uneven distribution of sensitive facial attributes such as age, gender, and race. In this paper, we introduce a novel approach to address this issue by debiasing the attributes in the images generated by diffusion models. Our approach involves disentangling facial attributes by localizing the means within the latent space of the diffusion model using Gaussian mixture models (GMM). This method, leveraging the adaptable latent structure of diffusion models, allows us to localize the subspace responsible for generating specific attributes on-the-fly without the need for retraining. We demonstrate the effectiveness of our technique across various face datasets, resulting in fairer data generation while preserving sample quality. Furthermore, we empirically illustrate its effectiveness in reducing bias in downstream classification tasks without compromising performance by augmenting the original dataset with fairly generated data.
B. Pal and A. Kannan—Indicates equal contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albiero, V., Zhang, K., Bowyer, K.W.: How does gender balance in training data affect face recognition accuracy? In: 2020 IEEE International Joint Conference on Biometrics (IJCB), pp. 1–10. IEEE (2020)
Albiero, V., Zhang, K., King, M.C., Bowyer, K.W.: Gendered differences in face recognition accuracy explained by hairstyles, makeup, and facial morphology. IEEE Trans. Inf. Forensics Secur. 17, 127–137 (2021)
Antoniou, A., Storkey, A., Edwards, H.: Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340 (2017)
Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)
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)
Calimeri, F., Marzullo, A., Stamile, C., Terracina, G.: Biomedical data augmentation using generative adversarial neural networks. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10614, pp. 626–634. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68612-7_71
Choi, K., Grover, A., Singh, T., Shu, R., Ermon, S.: Fair generative modeling via weak supervision. In: International Conference on Machine Learning, pp. 1887–1898. PMLR (2020)
Dhar, P., Gleason, J., Roy, A., Castillo, C.D., Chellappa, R.: Pass: protected attribute suppression system for mitigating bias in face recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15087–15096 (2021)
Dhar, P., Gleason, J., Roy, A., Castillo, C.D., Phillips, P.J., Chellappa, R.: Distill and de-bias: mitigating bias in face verification using knowledge distillation. arXiv preprint arXiv:2112.09786 (2021)
Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780–8794 (2021)
Duarte, A.C., et al.: Wav2pix: speech-conditioned face generation using generative adversarial networks. In: ICASSP, pp. 8633–8637 (2019)
Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Grover, A., et al.: Bias correction of learned generative models using likelihood-free importance weighting. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Guo, J., Lu, S., Cai, H., Zhang, W., Yu, Y., Wang, J.: Long text generation via adversarial training with leaked information. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840–6851 (2020)
Huang, Z., Chan, K.C., Jiang, Y., Liu, Z.: Collaborative diffusion for multi-modal face generation and editing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6080–6090 (2023)
Jain, N., Olmo, A., Sengupta, S., Manikonda, L., Kambhampati, S.: Imperfect imaganation: implications of GANs exacerbating biases on facial data augmentation and snapchat face lenses. Artif. Intell. 304, 103652 (2022)
Karkkainen, K., Joo, J.: Fairface: face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1548–1558 (2021)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110–8119 (2020)
Kashyap, R.: Inconsistency of the AIC rule for estimating the order of autoregressive models. IEEE Trans. Autom. Control 25(5), 996–998 (1980)
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)
Lee, J., Kim, E., Lee, J., Lee, J., Choo, J.: Learning debiased representation via disentangled feature augmentation. Adv. Neural. Inf. Process. Syst. 34, 25123–25133 (2021)
Liu, M.Y., Huang, X., Yu, J., Wang, T.C., Mallya, A.: Generative adversarial networks for image and video synthesis: algorithms and applications. Proc. IEEE 109(5), 839–862 (2021)
Luccioni, A.S., Akiki, C., Mitchell, M., Jernite, Y.: Stable bias: analyzing societal representations in diffusion models. arXiv preprint arXiv:2303.11408 (2023)
Maluleke, V.H., et al.: Studying bias in GANs through the lens of race. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13673, pp. 344–360. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19778-9_20
Michael, K., Abbas, R., Jayashree, P., Bandara, R.J., Aloudat, A.: Biometrics and AI bias. IEEE Trans. Technol. Soc. 3(1), 2–8 (2022)
Mittermaier, M., Raza, M.M., Kvedar, J.C.: Bias in AI-based models for medical applications: challenges and mitigation strategies. NPJ Digit. Med. 6(1), 113 (2023)
Müller-Franzes, G., et al.: A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis. Sci. Rep. 13(1), 12098 (2023)
Naik, R., Nushi, B.: Social biases through the text-to-image generation lens. arXiv preprint arXiv:2304.06034 (2023)
Ojha, U., et al.: Few-shot image generation via cross-domain correspondence. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10743–10752 (2021)
Perera, M.V., Patel, V.M.: Analyzing bias in diffusion-based face generation models. In: 2023 IEEE International Joint Conference on Biometrics (IJCB), pp. 1–10. IEEE (2023)
Ramaswamy, V.V., Kim, S.S., Russakovsky, O.: Fair attribute classification through latent space de-biasing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9301–9310 (2021)
Reynolds, D.A., et al.: Gaussian mixture models. Encyclopedia Biometrics 741(659-663) (2009)
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684–10695 (2022)
de Rosa, G.H., Papa, J.P.: A survey on text generation using generative adversarial networks. Pattern Recogn. 119, 108098 (2021)
Sauer, A., Schwarz, K., Geiger, A.: Stylegan-XL: scaling stylegan to large diverse datasets. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1–10 (2022)
Schwarz, G.: Estimating the dimension of a model. Ann. Stat. 461–464 (1978)
Sharmanska, V., Hendricks, L.A., Darrell, T., Quadrianto, N.: Contrastive examples for addressing the tyranny of the majority. arXiv preprint arXiv:2004.06524 (2020)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)
Singh, J., Gould, S., Zheng, L.: High-fidelity guided image synthesis with latent diffusion models. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5997–6006. IEEE (2023)
Stypułkowski, M., Vougioukas, K., He, S., Zieba, M., Petridis, S., Pantic, M.: Diffused heads: diffusion models beat GANs on talking-face generation. arXiv preprint arXiv:2301.03396 (2023)
Tan, S., Shen, Y., Zhou, B.: Improving the fairness of deep generative models without retraining. arXiv preprint arXiv:2012.04842 (2020)
Teo, C.T., Abdollahzadeh, M., Cheung, N.M.: Fair generative models via transfer learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 2429–2437 (2023)
Wang, A., Russakovsky, O.: Directional bias amplification. In: International Conference on Machine Learning, pp. 10882–10893. PMLR (2021)
Wilson, B., Hoffman, J., Morgenstern, J.: Predictive inequity in object detection. arXiv preprint arXiv:1902.11097 (2019)
Wu, H., Albiero, V., Krishnapriya, K., King, M.C., Bowyer, K.W.: Face recognition accuracy across demographics: shining a light into the problem. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1041–1050 (2023)
Yang, L., et al.: Diffusion models: a comprehensive survey of methods and applications. ACM Comput. Surv. 56(4), 1–39 (2023)
Zhang, F., et al.: Distributionally generative augmentation for fair facial attribute classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 22797–22808 (2024)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)
Acknowledgements
This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via [2022-21102100005]. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of ODNI, IARPA, or the U.S. Government. The US. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
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
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pal, B., Kannan, A., Kathirvel, R.P., O’Toole, A.J., Chellappa, R. (2025). GAMMA-FACE: GAussian Mixture Models Amend Diffusion Models for Bias Mitigation in Face Images. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15125. Springer, Cham. https://doi.org/10.1007/978-3-031-72855-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-72855-6_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72854-9
Online ISBN: 978-3-031-72855-6
eBook Packages: Computer ScienceComputer Science (R0)