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 2404.01030cs.CVcs.AIcs.CY
收藏

文本到图像生成中的偏见综述:定义、评估与缓解

Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation

University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

Yixin Wan, Arjun Subramonian, Anaelia Ovalle, Zongyu Lin, Ashima Suvarna, Christina Chance, Hritik Bansal, Rebecca Pattichis, Kai-Wei Chang

AI总结:

本文首次系统综述了文本到图像生成模型中的性别、肤色和地理文化偏见,梳理了定义、评估与缓解方法,指出现有研究在非二元性别、地理文化偏见、统一评估框架和全面缓解策略上的不足,并提出未来研究方向。

摘要:

近年来,具备文本到图像(T2I)生成能力的大型强大模型(如OpenAI的DALLE-3和Google的Gemini)的发展,使用户能够根据文本提示生成高质量图像。然而,越来越明显的是,即使是简单的提示也可能导致T2I模型在生成的图像中表现出明显的社会偏见。这种偏见可能在社会中导致分配性和代表性伤害,进一步边缘化少数群体。针对这一问题,近期大量研究致力于调查T2I系统中不同维度的偏见。然而,目前缺乏对这些研究的广泛综述,阻碍了对当前进展和研究空白的系统性理解。我们提出了首个关于T2I生成模型中偏见的广泛综述。在本综述中,我们回顾了关于偏见维度的先前研究:性别、肤色和地理文化。具体而言,我们讨论了这些工作如何定义、评估和缓解偏见的不同方面。我们发现:(1)虽然性别和肤色偏见被广泛研究,但地理文化偏见仍未得到充分探索;(2)大多数关于性别和肤色偏见的工作研究了职业关联,而其他方面则较少被研究;(3)几乎所有性别偏见研究都忽略了非二元性别身份;(4)评估数据集和指标分散,缺乏统一的偏见测量框架;(5)当前的缓解方法未能全面解决偏见。基于当前局限性,我们指出了未来的研究方向,以促进以人为中心的偏见定义、评估和缓解。我们希望强调研究T2I系统中偏见的重要性,并鼓励未来努力全面理解和应对偏见,为每个人构建公平且值得信赖的T2I技术。

英文摘要:

The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become increasingly evident that even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images. Such bias might lead to both allocational and representational harms in society, further marginalizing minority groups. Noting this problem, a large body of recent works has been dedicated to investigating different dimensions of bias in T2I systems. However, an extensive review of these studies is lacking, hindering a systematic understanding of current progress and research gaps. We present the first extensive survey on bias in T2I generative models. In this survey, we review prior studies on dimensions of bias: Gender, Skintone, and Geo-Culture. Specifically, we discuss how these works define, evaluate, and mitigate different aspects of bias. We found that: (1) while gender and skintone biases are widely studied, geo-cultural bias remains under-explored; (2) most works on gender and skintone bias investigated occupational association, while other aspects are less frequently studied; (3) almost all gender bias works overlook non-binary identities in their studies; (4) evaluation datasets and metrics are scattered, with no unified framework for measuring biases; and (5) current mitigation methods fail to resolve biases comprehensively. Based on current limitations, we point out future research directions that contribute to human-centric definitions, evaluations, and mitigation of biases. We hope to highlight the importance of studying biases in T2I systems, as well as encourage future efforts to holistically understand and tackle biases, building fair and trustworthy T2I technologies for everyone.

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。

↑