Racial Bias in AI-Generated Images
收藏CESSDA2024-09-03 更新2025-04-12 收录
下载链接:
https://datacatalogue.cessda.eu/detail?lang=en&q=fa9901bb818d96dc780715251ecb8b7f2e01794f6dd6f61f17c145cdc01569bf
下载链接
链接失效反馈官方服务:
资源简介:
This file is supplementary material for the manuscript Racial Bias in AI-Generated Images, which has been submitted to a peer-reviewed journal.This dataset/paper examined the image-to-image generation accuracy (i.e., the original race and gender of a person’s image were replicated in the new AI-generated image) of a Chinese AI-powered image generator. We examined the image-to-image generation models transforming the racial and gender categories of the original photos of White, Black and East Asian people (N =1260) in three different racial photo contexts: a single person, two people of the same race, and two people of different races. There are original images (e.g., WW1), AI-generated images (e.g., AM1_1, AM1_2, AM1_3), and SPSS files (Yang 230801 Racial bias in Meitu_Accuracy Paper.sav) in this dataset.
提供机构:
DANS Data Station Social Sciences and Humanities



