Understanding and Evaluating Racial Biases in Image Captioning
Open accessThe DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Abstract
Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in undesirable ways. In this work, we study bias propagation pathways within image captioning, focusing specifically on the COCO dataset. Prior work has analyzed gender bias in captions using automatically-derived gender labels; here we examine racial and intersectional biases using manual annotations. Our first contribution is in annotating the perceived gender and skin color of 28,315 of the depicted people after obtaining IRB approval. Using these annotations, we compare racial biases present in both manual and automatically-generated image captions. We demonstrate differences in caption performance, sentiment, and word choice between images of lighter versus darker-skinned people. Further, we find the magnitude of these differences to be greater in modern captioning systems compared to older ones, thus leading to concerns that without proper consideration and mitigation these differences will only become increasingly prevalent. Code and data is available at https://princetonvisualai.github.io/imagecaptioning-bias/.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“This work goes along with others that unveil biases present in existing algorithms [53, 49, 4].”
BackgroundShow and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318
VADER: a parsimonious rule-based model for sentiment analysis of social media text
Hutto, C., & Gilbert, E. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14550 · Cited by 6,087
College Admissions and the Stability of Marriage
Gale, D., & Shapley, L. S. (1962) · The American Mathematical Monthly · doi:10.1080/00029890.1962.11989827 · Cited by 5,985
The validity and practicality of sun-reactive skin types I through VI
Fitzpatrick, T. B. (1988) · Archives of Dermatology · doi:10.1001/archderm.1988.01670060015008 · Cited by 4,339
Algorithms of Oppression: How Search Engines Reinforce Racism
Noble, S. U. (2020) · doi:10.2307/j.ctt1pwt9w5 · Cited by 2,709
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×
“Researchers have advocated for increased transparency of datasets [27, 35], including developing tools to steer researcher intervention [8, 70].”
BackgroundSPICE: Semantic Propositional Image Caption Evaluation
Anderson, P., Fernando, B., Johnson, M., & Gould, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46454-1_24 · Cited by 1,986
Cited by
Flamingo: a visual language model for few-shot learning
Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1723 · Cited by 966
“Its ability to additionally handle visual inputs poses specific risks such as gender and racial biases relating to the contents of the input images, similar to a number of visual recognition systems [12, 21, 37, 97, 147].”
BackgroundVision-Language Pre-Training: Basics, Recent Advances, and Future Trends
Gan, Z., Li, L., Li, C., Wang, L., Liu, Z., & Gao, J. (2022) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000105 · Cited by 155
Large Language Models versus Natural Language Understanding and Generation
Karanikolas, N., Manga, E., Samaridi, N., Tousidou, E., & Vassilakopoulos, M. (2023) · Proceedings of the 27th Pan-Hellenic Conference on Progress in Computing and Informatics · doi:10.1145/3635059.3635104 · Cited by 102
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…”
BackgroundUnderstanding Gender Bias in AI-Generated Product Descriptions
Kelly, M., Tahaei, M., Smyth, P., & Wilcox, L. (2025) · Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3715275.3732169 · Cited by 4
Metadata
- Authors
- Zhao, D., Wang, A., & Russakovsky, O.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 14810-14820
- OpenAlex
- W3172872502
- Cited by
- 83
- References
- 40
- FWCI
- 14.09
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Understanding and Evaluating Racial Biases in Image Captioning. https://app.cochat.ai/papers/10.1109/iccv48922.2021.01456
- The paper
- Zhao, D., Wang, A., & Russakovsky, O. (2021). Understanding and Evaluating Racial Biases in Image Captioning. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv48922.2021.01456
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.