Fair Attribute Classification through Latent Space De-biasing
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes (e.g., gender, race) are known to learn and exploit those correlations. In this work, we introduce a method for training accurate target classifiers while mitigating biases that stem from these correlations. We use GANs to generate realistic-looking images, and perturb these images in the underlying latent space to generate training data that is balanced for each protected attribute. We augment the original dataset with this generated data, and empirically demonstrate that target classifiers trained on the augmented dataset exhibit a number of both quantitative and qualitative benefits. We conduct a thorough evaluation across multiple target labels and protected attributes in the CelebA dataset, and provide an in-depth analysis and comparison to existing literature in the space. Code can be found at https://github.com/princetonvisualai/gan-debiasing.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1×
“Over the past few years, a number of works [18, 24, 25, 27, 34] improved GANs to generate more realistic images with better stability.”
BackgroundImproved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Improved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800 · cited 1×
“Over the past few years, a number of works [18, 24, 25, 27, 34] improved GANs to generate more realistic images with better stability.”
BackgroundProgressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727
StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation
Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., & Choo, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00916 · Cited by 4,163
Self-citationEquality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 2×
“This is a stricter notion of equalized odds[19].”
BackgroundMan is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615 · cited 1×
“De-biasing models: The effect of gender and racial bias on AI models has been well documented [8, 9, 22, 40, 41].”
BackgroundBellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovic, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1810.01943 · Cited by 1,581
Mitigating Unwanted Biases with Adversarial Learning
Zhang, B. H., Lemoine, B., & Mitchell, M. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278779 · Cited by 1,387
Interpreting the Latent Space of GANs for Semantic Face Editing
Shen, Y., Gu, J., Tang, X., & Zhou, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00926 · Cited by 1,063
AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilović, A., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2942287 · Cited by 884
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1323 · Cited by 829 · cited 3×
“Multiple metrics have been proposed to measure fairness of a model [19, 44, 46, 10, 11] and each of these measures a different notion of fairness.”
BackgroundZafar, M. B., Valera, I., Gomez Rodriguez, M., & Gummadi, K. P. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052660 · Cited by 632 · cited 1×
“Multiple metrics have been proposed to measure fairness of a model [19, 44, 46, 10, 11] and each of these measures a different notion of fairness.”
BackgroundBuilding Classifiers with Independency Constraints
Calders, T., Kamiran, F., & Pechenizkiy, M. (2009) · 2009 IEEE International Conference on Data Mining Workshops · doi:10.1109/icdmw.2009.83 · Cited by 468 · cited 1×
“Multiple metrics have been proposed to measure fairness of a model [19, 44, 46, 10, 11] and each of these measures a different notion of fairness.”
BackgroundWomen Also Snowboard: Overcoming Bias in Captioning Models
Hendricks, L. A., Burns, K., Saenko, K., Darrell, T., & Rohrbach, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_47 · Cited by 404
FairGAN: Fairness-aware Generative Adversarial Networks
Xu, D., Yuan, S., Zhang, L., & Wu, X. (2018) · 2018 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2018.8622525 · Cited by 379
Yang, K., Qinami, K., Fei-Fei, L., Deng, J., & Russakovsky, O. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3375709 · Cited by 254
Self-citationFairness GAN: Generating datasets with fairness properties using a generative adversarial network
Sattigeri, P., Hoffman, S. C., Chenthamarakshan, V., & Varshney, K. R. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2945519 · Cited by 134
Directional Bias Amplification
Wang, A., & Russakovsky, O. (2021) · arXiv · doi:10.48550/arxiv.2102.12594 · Cited by 30 · cited 1×
“As our second fairness metric, we use the bias amplification (BA) metric proposed by Wang and Russakovsky [39].”
MethodSelf-citation
Cited by
A Survey of Machine Unlearning
Nguyen, T. T., Huynh, T. T., Ren, Z., Nguyen, P. L., Liew, A. W.-C., Yin, H., & Nguyen, Q. V. H. (2022) · arXiv · doi:10.48550/arxiv.2209.02299 · Cited by 193
Enhancing Fairness in Face Detection in Computer Vision Systems by Demographic Bias Mitigation
Yang, Y., Gupta, A., Feng, J., Singhal, P., Yadav, V., Wu, Y., Natarajan, P., Hedau, V., & Joo, J. (2022) · Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3514094.3534153 · Cited by 24
“Another line of work have used generated models to synthesize new images or modify existing ones which can be used to either augment unbalanced training dataset [38] or to measure model’s sensitivity to protected attributes [3, 13, 23].”
BackgroundXie, J., Yu, R., Zhang, H., Billah, S. M., Lee, S., & Carroll, J. M. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714210 · Cited by 23
Inspecting the Geographical Representativeness of Images from Text-to-Image Models
Basu, A., Babu, R. V., & Pruthi, D. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00474 · Cited by 21
“There is a growing body of work that critically analyzes the outputs of deep learning models in an attempt to discover and measure societal biases for various downstream applications including image classification [41, 22, 46], image captioning [47, 13], language generation [34, 33], face recognition [5, 9], image sea…”
BackgroundEvidence for Hypodescent in Visual Semantic AI
Wolfe, R., Banaji, M. R., & Caliskan, A. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533185 · Cited by 19
Metadata
- Authors
- Ramaswamy, V. V., Kim, S. S. Y., & Russakovsky, O.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 9297-9306
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3108989460
- Cited by
- 117
- References
- 20
- FWCI
- 22.44
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.