Documenting Patterns of Exoticism of Marginalized Populations within Text-to-Image Generators
Sourojit Ghosh, Sanjana Gautam, Pranav Venkit, and Avijit Ghosh

TL;DR
This paper investigates how text-to-image generators exoticize marginalized populations, especially from the Global South, revealing patterns of cultural overamplification and its implications for harm-aware AI development.
Contribution
It extends previous work on exoticism to analyze diverse global populations, highlighting biases in generated images and proposing community-centered improvements for GAI tools.
Findings
Global South images show cultural overamplification in attire
Exoticism patterns are present in Western and marginalized populations
Implications for harm-aware and community-centered GAI design
Abstract
A significant majority of AI fairness research studying the harmful outcomes of GAI tools have overlooked non-Western communities and contexts, necessitating a stronger coverage in this vein. We extend our previous work on exoticism (Ghosh et al., 2024) of 'Global South' countries from across the world, as depicted by GAI tools. We analyze generated images of individuals from 13 countries -- India, Bangladesh, Papua New Guinea, Egypt, Ethiopia, Tunisia, Sudan, Libya, Venezuela, Colombia, Indonesia, Honduras, and Mexico -- performing everyday activities (such as being at home, going to work, getting groceries, etc.), as opposed to images for the same activities being performed by persons from 3 'Global North' countries -- USA, UK, Australia. While outputs for 'Global North' demonstrate a difference across images and people clad in activity-appropriate attire, individuals from 'Global…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
