Disability Representations: Finding Biases in Automatic Image Generation

Yannis Tevissen
6/21/2024
cs.CVcs.CL

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Recent advancements in image generation technology have enabled widespread access to AI-generated imagery, prominently used in advertising, entertainment, and progressively in every form of visual content. However, these technologies often perpetuate societal biases. This study investigates the representation biases in popular image generation models towards people with disabilities (PWD). Through a comprehensive experiment involving several popular text-to-image models, we analyzed the depiction of disability. The results indicate a significant bias, with most generated images portraying disabled individuals as old, sad, and predominantly using manual wheelchairs. These findings highlight the urgent need for more inclusive AI development, ensuring diverse and accurate representation of PWD in generated images. This research underscores the importance of addressing and mitigating biases in AI models to foster equitable and realistic representations.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models

83% match2023

Creating Disability Story Videos with Generative AI: Motivation, Expression, and Sharing

82% match2026

Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs

81% match2025

Generative AI Carries Non-Democratic Biases and Stereotypes: Representation of Women, Black Individuals, Age Groups, and People with Disability in AI-Generated Images across Occupations

81% match2024

AccessEval: Benchmarking Disability Bias in Large Language Models

81% match2025

Hidden Bias in the Machine: Stereotypes in Text-to-Image Models

80% match2025

Cite this paper

@article{tevissen2024disability,
  title  = {Disability Representations: Finding Biases in Automatic Image Generation},
  author = {Yannis Tevissen},
  year   = {2024},
  eprint = {2406.14993},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.14993v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.14993.svg)](https://codeofpaper.com/paper/2406.14993)

Discussion