Interpretations, Representations, and Stereotypes of Caste within Text-to-Image Generators

• URL: http://arxiv.org/abs/2408.01590v1
• Date: Fri, 2 Aug 2024 22:06:41 GMT
• Title: Interpretations, Representations, and Stereotypes of Caste within Text-to-Image Generators
• Authors: Sourojit Ghosh,
• Abstract summary: This paper addresses interpretations, representations, and stereotypes surrounding a tragically underexplored context in T2I research: caste. We examine how the T2I Stable Diffusion displays people of various castes, and what professions they are depicted as performing. Our findings reveal how Stable Diffusion outputs perpetuate systems of 'castelessness', equating Indianness with high-castes and depicting caste-oppressed identities with markers of poverty.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The surge in the popularity of text-to-image generators (T2Is) has been matched by extensive research into ensuring fairness and equitable outcomes, with a focus on how they impact society. However, such work has typically focused on globally-experienced identities or centered Western contexts. In this paper, we address interpretations, representations, and stereotypes surrounding a tragically underexplored context in T2I research: caste. We examine how the T2I Stable Diffusion displays people of various castes, and what professions they are depicted as performing. Generating 100 images per prompt, we perform CLIP-cosine similarity comparisons with default depictions of an 'Indian person' by Stable Diffusion, and explore patterns of similarity. Our findings reveal how Stable Diffusion outputs perpetuate systems of 'castelessness', equating Indianness with high-castes and depicting caste-oppressed identities with markers of poverty. In particular, we note the stereotyping and representational harm towards the historically-marginalized Dalits, prominently depicted as living in rural areas and always at protests. Our findings underscore a need for a caste-aware approach towards T2I design, and we conclude with design recommendations.

Related papers

• "I don't see myself represented here at all": User Experiences of Stable Diffusion Outputs Containing Representational Harms across Gender Identities and Nationalities [4.4212441764241]
  We conduct the largest human subjects study of Stable Diffusion, with a combination of crowdsourced data from 133 crowdworkers and 14 semi-structured interviews across diverse countries and genders. We first demonstrate a large disconnect between user expectations for Stable Diffusion outputs with those generated, evidenced by a set of Stable Diffusion renditions of a Person' providing images far away from such expectations. We then extend this finding of general dissatisfaction into highlighting representational harms caused by Stable Diffusion upon our subjects, especially those with traditionally marginalized identities.
  arXiv  Detail & Related papers  (2024-08-02T22:37:50Z)
• Discriminative Probing and Tuning for Text-to-Image Generation [129.39674951747412]
  Text-to-image generation (T2I) often faces text-image misalignment problems such as relation confusion in generated images. We propose bolstering the discriminative abilities of T2I models to achieve more precise text-to-image alignment for generation. We present a discriminative adapter built on T2I models to probe their discriminative abilities on two representative tasks and leverage discriminative fine-tuning to improve their text-image alignment.
  arXiv  Detail & Related papers  (2024-03-07T08:37:33Z)
• The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects [58.27353205269664]
  We propose the Paired Stereotype Test (PST) framework, which queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities. PST queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities. Using PST, we evaluate two aspects of gender biases -- the well-known bias in gendered occupation and a novel aspect: bias in organizational power.
  arXiv  Detail & Related papers  (2024-02-16T21:32:27Z)
• Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models [72.06006736916821]
  We use synthetic images to probe two applications of text-to-image models, image editing and classification, for social bias. Using our methodology, we uncover meaningful and significant inter-sectional social biases in textitStable Diffusion, a state-of-the-art open-source text-to-image model. Our findings caution against the uninformed adoption of text-to-image foundation models for downstream tasks and services.
  arXiv  Detail & Related papers  (2023-12-05T14:36:49Z)
• 'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion [5.870257045294649]
  We study stereotypes embedded within one of the most popular text-to-image generators: Stable Diffusion. We examine what stereotypes of gender and nationality/continental identity does Stable Diffusion display in the absence of such information.
  arXiv  Detail & Related papers  (2023-10-30T19:57:01Z)
• Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models [18.201326983938014]
  Large Language Models (LLMs) can encode societal biases, exposing their users to representational harms. We quantify stereotypical bias in popular LLMs according to an Indian-centric frame through Indian-BhED, a first of its kind dataset. We find that the majority of LLMs tested have a strong propensity to output stereotypes in the Indian context.
  arXiv  Detail & Related papers  (2023-09-15T17:38:41Z)
• Social Biases through the Text-to-Image Generation Lens [9.137275391251517]
  Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software. We take a multi-dimensional approach to studying and quantifying common social biases as reflected in the generated images. We present findings for two popular T2I models: DALLE-v2 and Stable Diffusion.
  arXiv  Detail & Related papers  (2023-03-30T05:29:13Z)
• Stable Bias: Analyzing Societal Representations in Diffusion Models [72.27121528451528]
  We propose a new method for exploring the social biases in Text-to-Image (TTI) systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts. We leverage this method to analyze images generated by 3 popular TTI systems and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents.
  arXiv  Detail & Related papers  (2023-03-20T19:32:49Z)
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale [61.555788332182395]
  We investigate the potential for machine learning models to amplify dangerous and complex stereotypes. We find a broad range of ordinary prompts produce stereotypes, including prompts simply mentioning traits, descriptors, occupations, or objects.
  arXiv  Detail & Related papers  (2022-11-07T18:31:07Z)
• On Disentangled and Locally Fair Representations [95.6635227371479]
  We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. We learn a locally fair representation, such that, under the learned representation, the neighborhood of each sample is balanced in terms of the sensitive attribute.
  arXiv  Detail & Related papers  (2022-05-05T14:26:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.