ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation

no code implementations • 12 Jan 2024 • Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, Sunipa Dev

First, we show that stereotypical attributes in ViSAGe are thrice as likely to be present in generated images of corresponding identities as compared to other attributes, and that the offensiveness of these depictions is especially higher for identities from Africa, South America, and South East Asia.

Text-to-Image Generation

AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia

no code implementations • 19 May 2023 • Rida Qadri, Renee Shelby, Cynthia L. Bennett, Emily Denton

This paper presents a community-centered study of cultural limitations of text-to-image (T2I) models in the South Asian context.

Cultural Incongruencies in Artificial Intelligence

no code implementations • 19 Nov 2022 • Vinodkumar Prabhakaran, Rida Qadri, Ben Hutchinson

Artificial intelligence (AI) systems attempt to imitate human behavior.

Attribute