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

arXiv:2401.06310v2 Announce Type: replace
Abstract: Recent studies have shown that Text-to-Image (T2I) model generations can reflect social stereotypes present in the real world. However, existing approaches for evaluating stereotypes have a noticeable lack of coverage of global identity groups and their associated stereotypes. To address this gap, we introduce the ViSAGe (Visual Stereotypes Around the Globe) dataset to enable the evaluation of known nationality-based stereotypes in T2I models, across 135 nationalities. We enrich an existing textual stereotype resource by distinguishing …

abstract analysis arxiv coverage cs.cl cs.cv cs.cy gap global identity image image generation scale social stereotypes studies text text-to-image type visual world