Fetching the paper…
Reading the bibliography…
We evaluate the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for biases related to the marking of age, gender, and race or ethnicity.
Universals of language
Joseph Harold Greenberg. 1963 · 1963
Earlier work this paper cites.
Principles of phonology
Nikolai Sergeevich Trubetzkoy. 1969 · 1969
Earlier work this paper cites.
Verbal communication
Roman Jakobson. 1972 · 1972
Earlier work this paper cites.
Marked and unmarked: A choice between unequals in semiotic structure
Linda R Waugh. 1982 · 1982
Earlier work this paper cites.
On the predictiveness of Natural Morphology1
Wolfgang U Dressler. 1985 · 1985
Earlier work this paper cites.
The validity and practicality of sun-reactive skin types I through VI
Thomas B Fitzpatrick. 1988 · 1988
Earlier work this paper cites.
Morphological naturalness
Willi Mayerthaler. 1988 · 1988
Earlier work this paper cites.
Demarginalizing the intersection of race and sex: A black feminist critique of antidiscrimination doctrine, feminist theory and antiracist politics
Kimberlé Crenshaw. 1989 · 1989
Earlier work this paper cites.
Markedness: The evaluative superstructure of language
Edwin L Battistella et al · 1990
Earlier work this paper cites.
Mapping the margins: Intersectionality, identity politics, and violence against women of color
Kimberle Crenshaw. 1990 · 1990
Earlier work this paper cites.
Markedness in grammar: Distributional, communicative and cognitive correlates of syntactic structure
Talmy Givón. 1991 · 1991
Earlier work this paper cites.
Marked women, unmarked men
Deborah Tannen. 1993 · 1993
Earlier work this paper cites.
Sorting things out: Classification and its consequences
Geoffrey C Bowker and Susan Leigh Star. 2000 · 2000
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition . Ieee, 248–255
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009 · 2009
Earlier work this paper cites.
Devise: A deep visual-semantic embedding model
Andrea Frome, Greg Corrado, Jonathon Shlens, Samy Bengio, Jeffrey Dean, Marc’Aurelio Ranzato, and Tomas Mikolov. 2013 · 2013
Earlier work this paper cites.
An intersectional analysis of gender and ethnic stereotypes: Testing three hypotheses
Negin Ghavami and Letitia Anne Peplau. 2013 · 2013
Earlier work this paper cites.
Zero-Shot Learning Through Cross-Modal Transfer. In Advances in Neural Information Processing Systems . 935–943
Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng. 2013 · 2013
Earlier work this paper cites.
Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition . 770–778
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016 · 2016
Earlier work this paper cites.
Semantics derived automatically from language corpora contain human-like biases
Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. 2017 · 2017
Earlier work this paper cites.
Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency . PMLR, 77–91
Joy Buolamwini and Timnit Gebru. 2018 · 2018
Earlier work this paper cites.
Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) . 2556–2565
Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. 2018 · 2018
Earlier work this paper cites.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In 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) . Association for Computational Linguistics, Minneapolis, Minnesota, 4171–4186
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019 · 2019
Cited alongside, same era.
Visualbert: A simple and performant baseline for vision and language
Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019 · 2019
Cited alongside, same era.
ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In Proceedings of the 33rd International Conference on Neural Information Processing Systems . 13–23
Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019 · 2019
Cited alongside, same era.
On Measuring Social Biases in Sentence Encoders. In 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) . 622–628
Multimodal datasets: misogyny, pornography, and malignant stereotypes
Abeba Birhane, Vinay Uday Prabhu, and Emmanuel Kahembwe. 2021 · 2021
Later among the works it cites.
Documenting the english colossal clean crawled corpus
Jesse Dodge, Maarten Sap, Ana Marasovic, William Agnew, Gabriel Ilharco, Dirk Groeneveld, and Matt Gardner. 2021 · 2021
Later among the works it cites.
Multimodal neurons in artificial neural networks
Gabriel Goh, Nick Cammarata, Chelsea Voss, Shan Carter, Michael Petrov, Ludwig Schubert, Alec Radford, and Chris Olah. 2021 · 2021
Later among the works it cites.
Dodging Attack Using Carefully Crafted Natural Makeup
Nitzan Guetta, Asaf Shabtai, Inderjeet Singh, Satoru Momiyama, and Yuval Elovici. 2021 · 2021
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Chandler May, Alex Wang, Shikha Bordia, Samuel Bowman, and Rachel Rudinger. 2019 · 2019
Cited alongside, same era.
Language models are unsupervised multitask learners
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al · 2019
Cited alongside, same era.
The Woman Worked as a Babysitter: On Biases in Language Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . 3407–3412
Emily Sheng, Kai-Wei Chang, Prem Natarajan, and Nanyun Peng. 2019 · 2019
Cited alongside, same era.
Assessing social and intersectional biases in contextualized word representations
Yi Chern Tan and L Elisa Celis. 2019 · 2019
Cited alongside, same era.
Contrastive Representation Distillation. In International Conference on Learning Representations
Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2019 · 2019
Cited alongside, same era.
Balanced datasets are not enough: Estimating and mitigating gender bias in deep image representations. In Proceedings of the IEEE/CVF International Conference on Computer Vision . 5310–5319
Tianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, and Vicente Ordonez. 2019 · 2019
Cited alongside, same era.
Predictive inequity in object detection
Benjamin Wilson, Judy Hoffman, and Jamie Morgenstern. 2019 · 2019
Cited alongside, same era.
Generative pretraining from pixels. In International Conference on Machine Learning . PMLR, 1691–1703
Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020 · 2020
Cited alongside, same era.
Intersectionality
Patricia Hill Collins and Sirma Bilge. 2020 · 2020
Cited alongside, same era.
Wei Guo and Aylin Caliskan. 2021 · 2021
Later among the works it cites.
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V Le, Yunhsuan Sung, Zhen Li, and Tom Duerig. 2021 · 2021
Later among the works it cites.
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 . 1548–1558
Kimmo Karkkainen and Jungseock Joo. 2021 · 2021
Later among the works it cites.
Age Bias in Emotion Detection: An Analysis of Facial Emotion Recognition Performance on Young, Middle-Aged, and Older Adults. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society . 638–644
Eugenia Kim, De’Aira Bryant, Deepak Srikanth, and Ayanna Howard. 2021 · 2021
Later among the works it cites.
SLIP: Self-supervision meets Language-Image Pre-training
Norman Mu, Alexander Kirillov, David Wagner, and Saining Xie. 2021 · 2021
Later among the works it cites.
MUM: A new AI milestone for understanding information
Pandu Nayak. 2021 · 2021
Later among the works it cites.
Understanding the Representation and Representativeness of Age in AI Data Sets
Joon Sung Park, Michael S Bernstein, Robin N Brewer, Ece Kamar, and Meredith Ringel Morris. 2021 · 2021
Later among the works it cites.
Learning transferable visual models from natural language supervision
Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al · 2021
Later among the works it cites.
Zero-shot text-to-image generation
Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021 · 2021
Later among the works it cites.
Auto-essentialization: Gender in automated facial analysis as extended colonial project
Morgan Klaus Scheuerman, Madeleine Pape, and Alex Hanna. 2021 · 2021
Later among the works it cites.
LAION-400-Million Open Dataset
Christoph Schuhmann. 2021 · 2021
Later among the works it cites.
Image representations learned with unsupervised pre-training contain human-like biases. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency . 701–713
Ryan Steed and Aylin Caliskan. 2021 · 2021
Later among the works it cites.
Turing Bletchley: A Universal Image Language Representation model by Microsoft
Saurabh Tiwary. 2021 · 2021
Later among the works it cites.
Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
Jialu Wang, Yang Liu, and Xin Eric Wang. 2021a · 2021
Later among the works it cites.
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2021b · 2021
Later among the works it cites.
Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing . 518–532
Robert Wolfe and Aylin Caliskan. 2021 · 2021
Later among the works it cites.
Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations
Robert Wolfe and Aylin Caliskan. 2022 · 2022
Closest in time.