Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good.We study a unique gender bias in image search in this work: the search images are often gender-imbalanced for genderneutral natural language queries.We diagnose two typical image search models, the specialized model trained on in-domain datasets and the generalized representation model pretrained on massive image and text data across the internet.Both models suffer from severe gender bias.Therefore, we introduce two novel debiasing approaches: an in-processing fair sampling method to address the gender imbalance issue for training models, and a postprocessing feature clipping method base on mutual information to debias multimodal representations of pre-trained models.Extensive experiments on MS-COCO (Lin et al., 2014) and Flickr30K (Young et al., 2014) benchmarks show that our methods significantly reduce the gender bias in image search models.
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
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
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 4×
“…a growing demand and interests in proposing defenses, including regularizing disparate impact (Za-far et al., 2015) and disparate treatment (Hardt et al., 2016), promoting fairness through causal inference (Kusner et al., 2017), and adding fairness guarantees in recommendations and…”
BackgroundMethodInfluentialUNITER: UNiversal Image-TExt Representation Learning
Chen, Y.-C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., & Liu, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58577-8_7 · Cited by 2,055 · cited 1×
“…the large, pre-trained multimodal representation models, which effectively learn pre-trained image and text representations to accomplish down-stream applications (Bachman et al., 2019; Chen et al., 2020a,c; Gan et al., 2020; Chen et al., 2020d; Rad-1 Figure 1: Gender bias in image search.”
BackgroundCertifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Man 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 3×
“Fairness in Machine Learning A number of unfair treatments by machine learning models were reported recently (Angwin et al., 2016; Buolamwini and Gebru, 2018; Bolukbasi et al., 2016; Otterbacher et al., 2017), and the literature has observed a growing demand and interests in proposing defenses, including regularizing…”
BackgroundMicrosoft COCO Captions: Data Collection and Evaluation Server
Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Dollar, P., & Zitnick, C. L. (2015) · arXiv · doi:10.48550/arxiv.1504.00325 · Cited by 1,614 · cited 12×
“Model Bias Although the pre-trained CLIP model is evaluated without fine-tuning, we observe that it achieves a comparable recall performance with the SCAN model on MS-COCO and dominates the Flickr30K dataset.”
MethodInfluentialStacked Cross Attention for Image-Text Matching
Lee, K.-H., Chen, X., Hua, G., Hu, H., & He, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_13 · Cited by 1,402
Data preprocessing techniques for classification without discrimination
Kamiran, F., & Calders, T. (2012) · Knowledge and Information Systems · doi:10.1007/s10115-011-0463-8 · Cited by 1,305 · cited 2×
“pre-processing (KamiranFaisal and CaldersToon, 2012; Feldman et al., 2015; Calmon et al., 2017), inprocessing, and post-processing approaches.”
BackgroundA Reductions Approach to Fair Classification
Agarwal, A., Beygelzimer, A., Dudík, M., Langford, J., & Wallach, H. (2018) · arXiv · doi:10.48550/arxiv.1803.02453 · Cited by 1,288
Friedman, B., & Nissenbaum, H. (1996) · ACM Transactions on Information Systems · doi:10.1145/230538.230561 · Cited by 1,203 · cited 1×
“These information systems are biased when results are systematically slanted in unfair discrimination against protected groups (Friedman and Nissenbaum, 1996).”
Background
Cited by
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
Bianchi, F., Kalluri, P., Durmus, E., Ladhak, F., Cheng, M., Nozza, D., Hashimoto, T., Jurafsky, D., Zou, J., & Caliskan, A. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3594095 · Cited by 342
“software developer and housekeeper (Wang et al., 2021; Kay et al., 2015; Wonsek, 1992), and others reportedly have substantial demographic imbalances (U.”
BackgroundMethodDeAR: Debiasing Vision-Language Models with Additive Residuals
Seth, A., Hemani, M., & Agarwal, C. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00659 · Cited by 34
Evidence 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
- Wang, J., Liu, Y., & Wang, X.
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 1995-2008
- OpenAlex
- W3199396412
- Cited by
- 50
- References
- 19
- FWCI
- 8.12
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.151
- The paper
- Wang, J., Liu, Y., & Wang, X. (2021). Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.151
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.