arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.06313cs.CVcs.CY
收藏

文本到图像模型及其对不同民族参与活动的人的表示

Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activities

Prince Sattam bin Abdulaziz University(沙特王子萨塔姆·本·阿卜杜勒阿齐兹大学)

Abdulkareem Alsudais

AI总结:

研究分析了DALL-E 3和Gemini 3 Pro Preview在生成日常活动图像时对206个民族的表示,发现传统服饰在某些活动中不适用,且与地区和收入组相关联。

摘要:

本文研究了流行文本到图像(T2I)模型DALL-E 3和Gemini 3 Pro Preview在生成个体参与日常活动图像时对206个民族的表示。五种场景被开发,生成了2060张图像,输入提示指定了五种活动中的民族。聚合结果显示,28.4%的图像中人物穿着传统服饰,其中在某些活动中不适用。这种模式与地区显著相关,中东及北非和撒哈拉以南非洲受到不成比例影响,并与世界银行收入组相关联。相似的地区和收入关联模式在两个体育相关活动中也观察到。为了评估图像-文本对齐,使用CLIP、ALIGN和GPT-4.1 mini对9270对图像-提示进行了评分。被标记为传统服饰的图像在提示包含国家名称时获得了显著更高的对齐评分,当移除国家名称时,这种模式减弱或逆转。修订的提示分析显示,一个模型频繁插入“传统”一词(传统标记图像中为50.3%,其他为16.6%)。这些结果表明,这些表示模式可以通过图像生成器、评估模型和提示修订等管道组件塑造。

英文摘要:

This paper investigates how popular text-to-image (T2I) models, DALL-E 3 and Gemini 3 Pro Preview, depict people from 206 nationalities when prompted to generate images of individuals engaging in common everyday activities. Five scenarios were developed, and 2,060 images were generated using input prompts that specified nationalities across five activities. When aggregating across activities and models, results showed that 28.4% of the images depicted individuals wearing traditional attire, including attire that is impractical for the specified activities in several cases. This pattern was statistically significantly associated with regions, with the Middle East & North Africa and Sub-Saharan Africa disproportionately affected, and was also associated with World Bank income groups. Similar region- and income-linked patterns were observed for images labeled as depicting impractical attire in two athletics-related activities. To assess image-text alignment, CLIP, ALIGN, and GPT-4.1 mini were used to score 9,270 image-prompt pairs. Images labeled as featuring traditional attire received statistically significantly higher alignment scores when prompts included country names, and this pattern weakened or reversed when country names were removed. Revised prompt analysis showed that one model frequently inserted the word "traditional" (50.3% for traditional-labeled images vs. 16.6% otherwise). These results indicate that these representational patterns can be shaped by several components of the pipeline, including image generator, evaluation models, and prompt revision.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑