Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition. But do unsupervised computer vision models automatically learn implicit patterns and embed social biases that could have harmful downstream effects? We develop a novel method for quantifying biased associations between representations of social concepts and attributes in images. We find that state-of-the-art unsupervised models trained on ImageNet, a popular benchmark image dataset curated from internet images, automatically learn racial, gender, and intersectional biases. We replicate 8 previously documented human biases from social psychology, from the innocuous, as with insects and flowers, to the potentially harmful, as with race and gender. Our results closely match three hypotheses about intersectional bias from social psychology. For the first time in unsupervised computer vision, we also quantify implicit human biases about weight, disabilities, and several ethnicities. When compared with statistical patterns in online image datasets, our findings suggest that machine learning models can automatically learn bias from the way people are stereotypically portrayed on the web.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Mapping the Margins: Intersectionality, Identity Politics, and Violence against Women of Color
Crenshaw, K. (1991) · Stanford Law Review · doi:10.2307/1229039 · Cited by 32,792
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 1×
“These algorithms are used in important real-world settings, from applicant video screening [36, 61] to autonomous vehicles [29, 52], despite the fact that their harmful downstream effects have been documented in applications such as online ad delivery [67] and image captioning [39].”
MethodMomentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
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×
“As a qualitative case study, we selected 5 male-and 5 female-appearing artificial faces from a database [1] generated with StyleGAN [42].”
MethodMeasuring individual differences in implicit cognition: the implicit association test
Greenwald, A. G., McGhee, D. E., & Schwartz, J. L. K. (1998) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.74.6.1464 · Cited by 9,210
Understanding and using the Implicit Association Test: I. An improved scoring algorithm.
Greenwald, A. G., Nosek, B. A., & Banaji, M. R. (2003) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.85.2.197 · Cited by 5,815
Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.00982 · Cited by 3,653
Understanding and using the Implicit Association Test: III. Meta-analysis of predictive validity.
Greenwald, A. G., Poehlman, T. A., Uhlmann, E. L., & Banaji, M. R. (2009) · Journal of Personality and Social Psychology · doi:10.1037/a0015575 · Cited by 3,257
A Survey on Deep Transfer Learning
Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., & Liu, C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01424-7_27 · Cited by 3,165
Model Cards for Model Reporting
Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287596 · Cited by 2,681 · cited 1×
“Our method can be used to assess task-agnostic biases contained in a dataset to enhance transparency [28, 51], but bias mitigation for unsupervised transfer learning is a challenging open problem.”
MethodRevisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Daumé, H., & Crawford, K. (2018) · arXiv · doi:10.48550/arxiv.1803.09010 · Cited by 2,474
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., III, H. D., & Crawford, K. (2021) · Communications of the ACM · doi:10.1145/3458723 · Cited by 2,469 · cited 1×
“Our method can be used to assess task-agnostic biases contained in a dataset to enhance transparency [28, 51], but bias mitigation for unsupervised transfer learning is a challenging open problem.”
MethodHewstone, M., Rubin, M., & Willis, H. (2002) · Annual Review of Psychology · doi:10.1146/annurev.psych.53.100901.135109 · Cited by 2,031 · cited 1×
“There is a similar theory in social psychology: most bias takes the form of in-group favoritism, rather than out-group derogation [39].”
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×
“Several studies show that word embeddings, or representations, learned automatically from the way words co-occur in large text corpora exhibit human-like biases [8, 12, 27].”
BackgroundSelf-Supervised Learning of Pretext-Invariant Representations
Misra, I., & van der Maaten, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00674 · Cited by 1,435
Word embeddings quantify 100 years of gender and ethnic stereotypes
Garg, N., Schiebinger, L., Jurafsky, D., & Zou, J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1720347115 · Cited by 1,065 · cited 1×
“Several studies show that word embeddings, or representations, learned automatically from the way words co-occur in large text corpora exhibit human-like biases [8, 12, 27].”
BackgroundLanguage (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · cited 1×
“Do these unsupervised computer vision models embed human biases like their counterparts in natural language? If so, what are the origins of this bias? In NLP, embedding biases have been traced to word co-occurrences and other statistical patterns in text corpora used for training [12, 10, 7].”
BackgroundMitigating bias in algorithmic hiring: evaluating claims and practices
Raghavan, M., Barocas, S., Kleinberg, J., & Levy, K. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372828 · Cited by 845
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 2×
“As with static embeddings, researchers have shown that embeddings extracted from contextualized language models also exhibit downstream racial and gender biases [4, 34, 69, 79].”
BackgroundDo ImageNet Classifiers Generalize to ImageNet?
Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019) · arXiv · doi:10.48550/arxiv.1902.10811 · Cited by 790
Unequal Representation and Gender Stereotypes in Image Search Results for Occupations
Kay, M., Matuszek, C., & Munson, S. A. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702520 · Cited by 509 · cited 3×
“In image datasets and image search results, researchers have documented clear correlations between the presence of individuals of a certain gender and the presence of stereotypical objects; for instance, the category “male" co-occurs with career and office related content such as ties and suits whereas “female" more o…”
BackgroundResultOn Measuring Social Biases in Sentence Encoders
May, C., Wang, A., Bordia, S., Bowman, S. R., & Rudinger, R. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1063 · Cited by 461 · cited 4×
“The high dimensionality does not hinder our approach; association tests have been used with embeddings as large as 4, 096 dimensions [48].”
BackgroundMethodInfluentialWomen 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
Measuring Bias in Contextualized Word Representations
Kurita, K., Vyas, N., Pareek, A., Black, A. W., & Tsvetkov, Y. (2019) · Proceedings of the First Workshop on Gender Bias in Natural Language Processing · doi:10.18653/v1/w19-3823 · Cited by 348 · cited 1×
“In NLP, there are several systematic approaches to measuring bias in contextualized word embeddings [48, 69, 35, 9], some model-specific [45].”
BackgroundBias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
De-Arteaga, M., Romanov, A., Wallach, H., Chayes, J., Borgs, C., Chouldechova, A., Geyik, S., Kenthapadi, K., & Kalai, A. T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287572 · Cited by 337 · cited 1×
“If downstream applications use these representations to make consequential decisions about human beings, such as automated video job interview evaluations, artificial intelligence (AI) may perpetuate existing biases and exacerbate historical injustices [60, 19].”
BackgroundBias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
De-Arteaga, M., Romanov, A., Wallach, H., Chayes, J., Borgs, C., Chouldechova, A., Geyik, S., Kenthapadi, K., & Kalai, A. T. (2019) · arXiv · doi:10.48550/arxiv.1901.09451 · Cited by 337
Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing
Raji, I. D., Gebru, T., Mitchell, M., Buolamwini, J., Lee, J., & Denton, R. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375820 · Cited by 299 · cited 1×
“question answering [11, 43, 20, 76, 47, 52].”
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
Evaluating the Underlying Gender Bias in Contextualized Word Embeddings
Basta, C., Costa-jussà, M. R., & Casas, N. (2019) · Proceedings of the First Workshop on Gender Bias in Natural Language Processing · doi:10.18653/v1/w19-3805 · Cited by 189 · cited 2×
“As with static embeddings, researchers have shown that embeddings extracted from contextualized language models also exhibit downstream racial and gender biases [79, 5, 69, 35].”
BackgroundGuo, W., & Caliskan, A. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462536 · Cited by 180 · cited 7×
“Guo and Caliskan [34] dispense with sentence templates entirely, pooling across 𝑛 word-level contextual embeddings for the same token extracted from random sentences.”
BackgroundInfluentialSelf-citationPseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
Arazo, E., Ortego, D., Albert, P., O'Connor, N. E., & McGuinness, K. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207304 · Cited by 77
Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing
Raji, I. D., Gebru, T., Mitchell, M., Buolamwini, J., Lee, J., & Denton, E. (2020) · arXiv · doi:10.48550/arxiv.2001.00964 · Cited by 69
Voita, E., Sennrich, R., & Titov, I. (2019) · arXiv · doi:10.48550/arxiv.1909.01380 · Cited by 17
Cited by
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Schramowski, P., Brack, M., Deiseroth, B., & Kersting, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02157 · Cited by 219
“These concerns include, for instance, models producing stereotypical and derogatory content [3] and gender and racial biases [10, 24, 38, 41].”
BackgroundAI auditing: The Broken Bus on the Road to AI Accountability
Birhane, A., Steed, R., Ojewale, V., Vecchione, B., & Raji, I. D. (2024) · 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml59370.2024.00037 · Cited by 158
Self-citationMuse: Text-To-Image Generation via Masked Generative Transformers
Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.-H., Murphy, K., Freeman, W. T., Rubinstein, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.00704 · Cited by 157
“However, it is well known that they can also be leveraged for misinformation, harassment and various types of social and cultural biases (Franks & Waldman, 2018; Whittaker et al., 2020; Srinivasan & Uchino, 2021; Steed & Caliskan, 2021).”
BackgroundInvestigating Gender and Racial Biases in DALL-E Mini Images
Cheong, M., Abedin, E., Ferreira, M., Reimann, R., Chalson, S., Robinson, P., Byrne, J., Ruppanner, L., Alfano, M., & Klein, C. (2024) · ACM Journal on Responsible Computing · doi:10.1145/3649883 · Cited by 57
“Gaining a clearer understanding of the extent to which multi-modal generative models are biased, what sorts of biases they perpetuate, and who sufers most at the hands of biased representation is of critical import [12, 73].”
BackgroundResultWolfe, R., Yang, Y., Howe, B., & Caliskan, A. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594072 · Cited by 42
Self-citation
Metadata
- Authors
- Steed, R., & Caliskan, A.
- Venue
- Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2021-03
- Pages
- 701-713
- OpenAlex
- W3095351420
- Cited by
- 157
- References
- 41
- FWCI
- 33.66
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.