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.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
- 2021. Generated Photos. https://generated.photosGoogle Scholar
- Eric Arazo, Diego Ortego, Paul Albert, Noel E. O'Connor, and Kevin McGuinness. 2020. Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning. In Proceedings of the International Joint Conference on Neural Networks. Institute of Electrical and Electronics Engineers Inc., 1--8. https://doi.org/10. 1109/IJCNN48605.2020.9207304Google ScholarCross Ref
- Philip Bachman, R Devon Hjelm, and William Buchwalter. 2019. Learning Representations by Maximizing Mutual Information Across Views. In Advances in Neural Information Processing Systems, H Wallach, H Larochelle, A Beygelzimer, F d Alché-Buc, E Fox, and R Garnett (Eds.), Vol. 32. Curran Associates, Inc., 15535--15545. https://proceedings.neurips.cc/paper/2019/file/ddf354219aac374f1d40b7e760ee5bb7-Paper.pdfGoogle Scholar
- Christine Basta, Marta R Costa-jussà, and Noe Casas. 2019. Evaluating the Underlying Gender Bias in Contextualized Word Embeddings. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics, Florence, Italy, 33--39. https://doi.org/10.18653/v1/W19-3805Google ScholarCross Ref
- Francis S. Bellezza, Anthony G. Greenwald, and Mahzarin R. Banaji. 1986. Words high and low in pleasantness as rated by male and female college students. Behavior Research Methods, Instruments, & Computers 18, 3 (5 1986), 299--303. https://doi.org/10.3758/BF03204403Google Scholar
- Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. 2020. Language (Technology) is Power: A Critical Survey of "Bias" in NLP. arXiv preprint arXiv:2005.14050 (2020).Google Scholar
- Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. In Advances in Neural Information Processing Systems 29, D D Lee, M Sugiyama, U V Luxburg, I Guyon, and R Garnett (Eds.). Curran Associates, Inc., 4349--4357. http://papers.nips.cc/paper/6228-man-is-to-computer-programmer-as-woman-is-to-homemaker-debiasing-word-embeddings.pdfGoogle Scholar
- Rishi Bommasani, Kelly Davis, and Claire Cardie. 2020. Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (ACL), 4758--4781. https://doi.org/10.18653/v1/2020.acl-main.431Google ScholarCross Ref
- Marc-Etienne Brunet, Colleen Alkalay-Houlihan, Ashton Anderson, and Richard Zemel. 2019. Understanding the Origins of Bias in Word Embeddings. In Proceedings of the 36th International Conference on Machine Learning. PMLR, 803--811. http://proceedings.mlr.press/v97/brunet19a.htmlGoogle Scholar
- Joy Buolamwini and Timnit Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research, Vol. 81), Sorelle A Friedler and Christo Wilson (Eds.). PMLR, New York, NY, USA, 77--91. http://proceedings.mlr.press/v81/buolamwini18a.htmlGoogle Scholar
- Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017. Semantics Derived Automatically from Language Corpora Contain Human-like Biases. Technical Report 6334. Science. 183--186 pages. https://doi.org/10.1126/science.aal4230Google Scholar
- Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-End Object Detection with Transformers. arXiv preprint arXiv:2005.12872 (2020).Google Scholar
- George H Chen. 2020. Deep Kernel Survival Analysis and Subject-Specific Survival Time Prediction Intervals. In Proceedings of the 5th Machine Learning for Healthcare Conference (Proceedings of Machine Learning Research, Vol. 126), Finale Doshi-Velez, Jim Fackler, Ken Jung, David Kale, Rajesh Ranganath, Byron Wallace, and Jenna Wiens (Eds.). PMLR, Virtual, 537--565. http://proceedings. mlr.press/v126/chen20a.htmlGoogle Scholar
- Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative Pretraining From Pixels. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daumé III and Aarti Singh (Eds.). PMLR, 1691--1703. http://proceedings.mlr.press/v119/chen20s.htmlGoogle Scholar
- Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daumé III and Aarti Singh (Eds.). PMLR, 1597--1607. http://proceedings.mlr.press/v119/chen20j.htmlGoogle Scholar
- Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, and Geoffrey Hinton. 2020. Big self-supervised models are strong semi-supervised learners. arXiv preprint arXiv:2006.10029 (2020).Google Scholar
- Kimberle Crenshaw. 1990. Mapping the margins: Intersectionality, identity politics, and violence against women of color. Stan. L. Rev. 43 (1990), 1241.Google ScholarCross Ref
- Maria De-Arteaga, Alexey Romanov, Hanna Wallach, Jennifer Chayes, Christian Borgs, Alexandra Chouldechova, Sahin Geyik, Krishnaram Kenthapadi, and Adam Tauman Kalai. 2019. Bias in bios: A case study of semantic representation bias in a high-stakes setting. In Proceedings of the Conference on Fairness, Accountability, and Transparency. ACM, 120--128.Google ScholarDigital Library
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).Google Scholar
- Jeff Donahue and Karen Simonyan. 2019. Large Scale Adversarial Representation Learning. In Advances in Neural Information Processing Systems, H Wallach, H Larochelle, A Beygelzimer, F d Alché-Buc, E Fox, and R Garnett (Eds.), Vol. 32. Curran Associates, Inc., 10542--10552. https://proceedings.neurips.cc/paper/2019/file/18cdf49ea54eec029238fcc95f76ce41-Paper.pdfGoogle Scholar
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. https://openreview.net/forum?id=YicbFdNTTyGoogle Scholar
- Alice H Eagly, Antonio Mladinic, and Stacey Otto. 1991. Are women evaluated more favorably than men?: An analysis of attitudes, beliefs, and emotions. Psychology of Women Quarterly 15, 2 (1991), 203--216.Google ScholarCross Ref
- Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. 2010. Why Does Unsupervised Pre-training Help Deep Learning? Journal of Machine Learning Research 11, 19 (2010), 625--660. http://jmlr.org/papers/v11/erhan10a.htmlGoogle ScholarDigital Library
- Dumitru Erhan, Pierre-Antoine Manzagol, Yoshua Bengio, Samy Bengio, and Pascal Vincent. 2009. The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training. In Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 5), David van Dyk and Max Welling (Eds.). PMLR, Hilton Clearwater Beach Resort, Clearwater Beach, Florida USA, 153--160. http://proceedings.mlr. press/v5/erhan09a.htmlGoogle Scholar
- Francesco Foroni and Tarik Bel-Bahar. 2010. Picture-IAT versus word-IAT: Level of stimulus representation influences on the IAT. European Journal of Social Psychology 40, 2 (3 2010), 321--337. https://doi.org/10.1002/ejsp.626Google Scholar
- Nikhil Garg, Londa Schiebinger, Dan Jurafsky, and James Zou. 2018. Word embeddings quantify 100 years of gender and ethnic stereotypes. Proceedings of the National Academy of Sciences of the United States of America 115, 16 (4 2018), E3635-E3644. https://doi.org/10.1073/pnas.1720347115Google ScholarCross Ref
- Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daumé III, and Kate Crawford. 2018. Datasheets for datasets. arXiv preprint arXiv:1803.09010 (2018).Google Scholar
- Andreas Geiger, Philip Lenz, and Raquel Urtasun. 2012. Are we ready for autonomous driving? the KITTI vision benchmark suite. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 3354--3361. https://doi.org/10.1109/CVPR.2012.6248074Google ScholarCross Ref
- Negin Ghavami and Letitia Anne Peplau. 2013. An intersectional analysis of gender and ethnic stereotypes: Testing three hypotheses. Psychology of Women Quarterly 37, 1 (2013), 113--127.Google ScholarCross Ref
- Kaitlin A Graff, Sarah K Murnen, and Anna K Krause. 2013. Low-cut shirts and high-heeled shoes: Increased sexualization across time in magazine depictions of girls. Sex roles 69, 11-12 (2013), 571--582.Google Scholar
- A G Greenwald, D E McGhee, and J L Schwartz. 1998. Measuring Individual Differences in Implicit Cognition: The Implicit Association Test. Journal of Personality and Social Psychology 74, 6 (6 1998), 1464--80. http://www.ncbi.nlm. nih.gov/pubmed/9654756Google ScholarCross Ref
- Anthony G. Greenwald, Brian A. Nosek, and Mahzarin R. Banaji. 2003. Understanding and Using the Implicit Association Test: I. An Improved Scoring Algorithm. Journal of Personality and Social Psychology 85, 2 (8 2003), 197--216. https://doi.org/10.1037/0022-3514.85.2.197Google Scholar
- Anthony G Greenwald, T Andrew Poehlman, Eric Luis Uhlmann, and Mahzarin R Banaji. 2009. Understanding and using the Implicit Association Test: III. Meta-analysis of predictive validity. Journal of personality and social psychology 97, 1 (2009), 17.Google ScholarCross Ref
- Wei Guo and Aylin Caliskan. 2020. Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases. arXiv preprint arXiv:2006.03955 (2020).Google Scholar
- Drew Harwell. 2019. A face-scanning algorithm increasingly decides whether you deserve the job. https://www.washingtonpost.com/technology/2019/10/22/ai-hiring-face-scanning-algorithm-increasingly-decides-whether-you-deserve-job/Google Scholar
- Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 9729--9738.Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 770--778. http://image-net.org/challenges/LSVRC/2015/Google ScholarCross Ref
- Lisa Anne Hendricks, Kaylee Burns, Kate Saenko, Trevor Darrell, and Anna Rohrbach. 2018. Women also snowboard: Overcoming bias in captioning models. In European Conference on Computer Vision. 793--811.Google ScholarDigital Library
- Miles Hewstone, Mark Rubin, and Hazel Willis. 2002. Intergroup bias. Annual review of psychology 53, 1 (2002), 575--604.Google Scholar
- Kashmir Hill. 2020. The Secretive Company That Might End Privacy as We Know It. https://www.nytimes.com/2020/01/18/technology/clearview-privacy-facial-recognition.htmlGoogle Scholar
- Corinne Iozzio. 2016. The Playboy Centerfold That Revolutionized Image-Processing Research. The Atlantic (2 2016). https://www.theatlantic.com/technology/archive/2016/02/lena-image-processing-playboy/461970/Google Scholar
- Tero Karras, Samuli Laine, and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4401--4410.Google ScholarCross Ref
- Matthew Kay, Cynthia Matuszek, and Sean A. Munson. 2015. Unequal Representation and Gender Stereotypes in Image Search Results for Occupations. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems - CHI '15. ACM Press, New York, New York, USA, 3819--3828. https://doi.org/10.1145/2702123.2702520Google ScholarDigital Library
- Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Technical Report. University of Toronto. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdfGoogle Scholar
- Keita Kurita, Nidhi Vyas, Ayush Pareek, Alan W Black, and Yulia Tsvetkov. 2019. Measuring Bias in Contextualized Word Representations. In Proceedings of the First Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics (ACL), Florence, Italy, 166--172. https://doi.org/10.18653/v1/w19-3823Google ScholarCross Ref
- Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper Uijlings, Ivan Krasin, Jordi Pont-Tuset, Shahab Kamali, Stefan Popov, Matteo Malloci, Tom Duerig, and others. 2018. The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. arXiv preprint arXiv:1811.00982 (2018).Google Scholar
- Varun Manjunatha, Nirat Saini, and Larry S Davis. 2019. Explicit Bias Discovery in Visual Question Answering Models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE.Google ScholarCross Ref
- Chandler May, Alex Wang, Shikha Bordia, Samuel R. Bowman, and Rachel Rudinger. 2019. On Measuring Social Biases in Sentence Encoders. In Proceedings of the 2019 Conference of the North. Association for Computational Linguistics, Stroudsburg, PA, USA, 622--628. https://doi.org/10.18653/v1/N19-1063Google ScholarCross Ref
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013).Google Scholar
- Ishan Misra and Laurens Van Der Maaten. 2020. Self-Supervised Learning of Pretext-Invariant Representations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 6707--6717.Google ScholarCross Ref
- Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, and Timnit Gebru. 2019. Model Cards for Model Reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency (FAT* '19). Association for Computing Machinery, New York, NY, USA, 220--229. https://doi.org/10.1145/3287560.3287596Google ScholarDigital Library
- Francesco Nex and Fabio Remondino. 2014. UAV for 3D mapping applications: A review., 15 pages. https://doi.org/10.1007/s12518-013-0120-xGoogle Scholar
- Brian A. Nosek and Mahzarin R. Banaji. 2001. The GO/NO-GO Association Task. Social Cognition 19, 6 (12 2001), 625--664. https://doi.org/10.1521/soco.19.6.625.20886Google Scholar
- Brian A. Nosek, Mahzarin R. Banaji, and Anthony G. Greenwald. 2002. Harvesting implicit group attitudes and beliefs from a demonstration web site. Group Dynamics 6, 1 (2002), 101--115. https://doi.org/10.1037/1089-2699.6.1.101Google ScholarCross Ref
- Brian A Nosek, Anthony G Greenwald, and Mahzarin R Banaji. 2007. The Implicit Association Test at Age 7: A Methodological and Conceptual Review. In Automatic processes in social thinking and behavior, J. A. Bargh (Ed.). Psychology Press, Chapter 6, 265--292.Google Scholar
- Brian A. Nosek, Frederick L. Smyth, Jeffrey J. Hansen, Thierry Devos, Nicole M. Lindner, Kate A. Ranganath, Colin Tucker Smith, Kristina R. Olson, Dolly Chugh, Anthony G. Greenwald, and Mahzarin R. Banaji. 2007. Pervasiveness and correlates of implicit attitudes and stereotypes. European Review of Social Psychology 18, 1 (11 2007), 36--88. https://doi.org/10.1080/10463280701489053Google ScholarCross Ref
- Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Doha, Qatar, 1532--1543. https://doi.org/10.3115/v1/D14-1162Google ScholarCross Ref
- Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep Contextualized Word Representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics, New Orleans, Louisiana, 2227--2237. https://doi.org/10.18653/v1/N18-1202Google ScholarCross Ref
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.Google Scholar
- Manish Raghavan, Solon Barocas, Jon Kleinberg, and Karen Levy. 2020. Mitigating bias in algorithmic hiring: Evaluating claims and practices. In FAT* 2020 -Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. Association for Computing Machinery, Inc, 469--481. https://doi.org/10.1145/3351095.3372828Google ScholarDigital Library
- Inioluwa Deborah Raji, Timnit Gebru, Margaret Mitchell, Joy Buolamwini, Joonseok Lee, and Emily Denton. 2020. Saving face: Investigating the ethical concerns of facial recognition auditing. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. ACM, 145--151.Google ScholarDigital Library
- Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar. 2019. Do ImageNet Classifiers Generalize to ImageNet?. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 5389--5400. http://proceedings.mlr.press/v97/recht19a.htmlGoogle Scholar
- Olga Russakovsky, Jia Deng, Zhiheng Huang, Alexander C Berg, and Li Fei-Fei. 2013. Detecting avocados to zucchinis: what have we done, and where are we going?. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2064--2071.Google ScholarDigital Library
- Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. 2015. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision 115, 3 (12 2015), 211--252. https://doi.org/10.1007/s11263-015-0816-yGoogle ScholarDigital Library
- Stefan Schweiger, Aileen Oeberst, and Ulrike Cress. 2014. Confirmation bias in web-based search: A randomized online study on the effects of expert information and social tags on information search and evaluation. Journal of Medical Internet Research 16, 3 (2014), -undefined. https://doi.org/10.2196/jmir.3044Google ScholarCross Ref
- Chen Sun, Abhinav Shrivastava, Saurabh Singh, and Abhinav Gupta. 2017. Revisiting unreasonable effectiveness of data in deep learning era. In Proceedings of the IEEE international conference on computer vision. IEEE, 843--852.Google ScholarCross Ref
- L Sweeney. 1997. Weaving technology and policy together to maintain confidentiality (vol 25, pg 2, 1997). Journal Of Law Medicine & Ethics 25, 4 (1997), 327.Google ScholarCross Ref
- Chuanqi Tan, Fuchun Sun, Tao Kong, Wenchang Zhang, Chao Yang, and Chunfang Liu. 2018. A survey on deep transfer learning. In International conference on artificial neural networks. IEEE, 270--279.Google ScholarCross Ref
- Yi Chern Tan and L Elisa Celis. 2019. Assessing Social and Intersectional Biases in Contextualized Word Representations. In Advances in Neural Information Processing Systems, H Wallach, H Larochelle, A Beygelzimer, F d Alché-Buc, E Fox, and R Garnett (Eds.), Vol. 32. Curran Associates, Inc., 13230--13241. https://proceedings.neurips.cc/paper/2019/file/201d546992726352471cfea6b0df0a48-Paper.pdfGoogle Scholar
- Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R Bowman, Dipanjan Das, and others. 2019. What do you learn from context? probing for sentence structure in contextualized word representations. arXiv preprint arXiv:1905.06316 (2019).Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems, I Guyon, U V Luxburg, S Bengio, H Wallach, R Fergus, S Vishwanathan, and R Garnett (Eds.), Vol. 30. Curran Associates, Inc., 5998--6008. https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdfGoogle Scholar
- Elena Voita, Rico Sennrich, and Ivan Titov. 2019. The bottom-up evolution of representations in the transformer: A study with machine translation and language modeling objectives. arXiv preprint arXiv:1909.01380 (2019).Google Scholar
- A Wang, A Narayanan, and O Russakovsky. 2020. REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets. In European Conference on Computer Vision.Google Scholar
- Tianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, and Vicente Ordonez. 2019. Balanced datasets are not enough: Estimating and mitigating gender bias in deep image representations. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, 5310--5319.Google ScholarCross Ref
- Zeyu Wang, Klint Qinami, Ioannis Christos Karakozis, Kyle Genova, Prem Nair, Kenji Hata, and Olga Russakovsky. 2020. Towards fairness in visual recognition: Effective strategies for bias mitigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 8919--8928.Google ScholarCross Ref
- Benjamin Wilson, Judy Hoffman, and Jamie Morgenstern. 2019. Predictive Inequity in Object Detection. arXiv preprint arXiv:1902.11097 (2 2019). http://arxiv.org/abs/1902.11097Google Scholar
- Kaiyuan Xu, Brian Nosek, and Anthony Greenwald. 2014. Data from the Race Implicit Association Test on the Project Implicit Demo Website. Journal of Open Psychology Data 2, 1 (3 2014), e3. https://doi.org/10.5334/jopd.acGoogle Scholar
- Kaiyu Yang, Klint Qinami, Li Fei-Fei, Jia Deng, and Olga Russakovsky. 2020. Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (FAT* '20). Association for Computing Machinery, New York, NY, USA, 547--558. https://doi.org/10.1145/3351095.3375709Google ScholarDigital Library
- Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai Wei Chang. 2017. Men also like shopping: Reducing gender bias amplification using corpus-level constraints. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2979--2989. https://doi.org/10.18653/v1/d17-1323Google ScholarCross Ref
Index Terms
- Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Recommendations
Measuring Subconscious Gender Biases against Male and Female Virtual Agents in Japan
HAI '22: Proceedings of the 10th International Conference on Human-Agent InteractionThis study aimed to investigate whether Japanese participants have subconscious gender biases against a male and a female virtual agents and quantify those biases if any. The participants were given a negative feedback after taking a logical thinking ...
Unsupervised Learning of Human Action Categories in Still Images with Deep Representations
In this article, we propose a novel method for unsupervised learning of human action categories in still images. In contrast to previous methods, the proposed method explores distinctive information of actions directly from unlabeled image databases, ...
Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases
AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and SocietyWith the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models generate dynamic word embeddings ...
Comments