A new evaluation framework reports that nine popular text-to-image models mostly fail equal-representation fairness criteria, with skintone alignment errors far larger than gender errors.
Easily accessible text-to-image generation amplifies demographic stereotypes at large scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models
A new evaluation framework reports that nine popular text-to-image models mostly fail equal-representation fairness criteria, with skintone alignment errors far larger than gender errors.