'Person' == Light-skinned, Western Man, and Sexualization of Women of
Color: Stereotypes in Stable Diffusion
- URL: http://arxiv.org/abs/2310.19981v2
- Date: Fri, 10 Nov 2023 18:47:20 GMT
- Title: 'Person' == Light-skinned, Western Man, and Sexualization of Women of
Color: Stereotypes in Stable Diffusion
- Authors: Sourojit Ghosh, Aylin Caliskan
- Abstract summary: 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.
- Score: 5.870257045294649
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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 i.e. what gender and nationality/continental identity is
assigned to `a person', or to `a person from Asia'. Using vision-language model
CLIP's cosine similarity to compare images generated by CLIP-based Stable
Diffusion v2.1 verified by manual examination, we chronicle results from 136
prompts (50 results/prompt) of front-facing images of persons from 6 different
continents, 27 nationalities and 3 genders. We observe how Stable Diffusion
outputs of `a person' without any additional gender/nationality information
correspond closest to images of men and least with persons of nonbinary gender,
and to persons from Europe/North America over Africa/Asia, pointing towards
Stable Diffusion having a concerning representation of personhood to be a
European/North American man. We also show continental stereotypes and resultant
harms e.g. a person from Oceania is deemed to be Australian/New Zealander over
Papua New Guinean, pointing to the erasure of Indigenous Oceanic peoples, who
form a majority over descendants of colonizers both in Papua New Guinea and in
Oceania overall. Finally, we unexpectedly observe a pattern of
oversexualization of women, specifically Latin American, Mexican, Indian and
Egyptian women relative to other nationalities, measured through an NSFW
detector. This demonstrates how Stable Diffusion perpetuates Western
fetishization of women of color through objectification in media, which if left
unchecked will amplify this stereotypical representation. Image datasets are
made publicly available.
Related papers
- The Male CEO and the Female Assistant: Gender Biases in Text-To-Image Generation of Dual Subjects [58.27353205269664]
We propose the Paired Stereotype Test (PST) framework to systematically evaluate T2I models in dual-subject generation setting.
PST is a dual-subject generation task, i.e. generating two people in the same image.
We show that despite generating seemingly fair or even anti-stereotype single-person images, DALLE-3 still shows notable biases under PST.
arXiv Detail & Related papers (2024-02-16T21:32:27Z) - AI-generated faces influence gender stereotypes and racial homogenization [1.6647208383676708]
We document significant biases in Stable Diffusion across six races, two genders, 32 professions, and eight attributes.
This analysis reveals significant racial homogenization depicting nearly all middle eastern men as dark-skinned, bearded, and wearing a traditional headdress.
Using a preregistered experiment, we show that being presented with inclusive AI-generated faces reduces people's racial and gender biases, while being presented with non-inclusive ones increases such biases.
arXiv Detail & Related papers (2024-02-01T20:32:14Z) - ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation [24.862839173648467]
We introduce the ViSAGe dataset to enable the evaluation of nationality-based stereotypes in T2I models.
We show that stereotypical attributes in ViSAGe are thrice as likely to be present in generated images of corresponding identities as compared to other attributes.
arXiv Detail & Related papers (2024-01-12T00:43:57Z) - Stable Diffusion Exposed: Gender Bias from Prompt to Image [28.88676131961107]
We introduce an evaluation protocol designed to analyze the impact of gender indicators on Stable Diffusion images.
Our findings include the existence of differences in the depiction of objects, such as instruments tailored for specific genders.
We also reveal that neutral prompts tend to produce images more aligned with masculine prompts than their feminine counterparts.
arXiv Detail & Related papers (2023-12-05T10:12:59Z) - VisoGender: A dataset for benchmarking gender bias in image-text pronoun
resolution [80.57383975987676]
VisoGender is a novel dataset for benchmarking gender bias in vision-language models.
We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas.
We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
arXiv Detail & Related papers (2023-06-21T17:59:51Z) - Stereotypes and Smut: The (Mis)representation of Non-cisgender
Identities by Text-to-Image Models [6.92043136971035]
We investigate how multimodal models handle diverse gender identities.
We find certain non-cisgender identities are consistently (mis)represented as less human, more stereotyped and more sexualised.
These improvements could pave the way for a future where change is led by the affected community.
arXiv Detail & Related papers (2023-05-26T16:28:49Z) - 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) - Auditing Gender Presentation Differences in Text-to-Image Models [54.16959473093973]
We study how gender is presented differently in text-to-image models.
By probing gender indicators in the input text, we quantify the frequency differences of presentation-centric attributes.
We propose an automatic method to estimate such differences.
arXiv Detail & Related papers (2023-02-07T18:52:22Z) - How well can Text-to-Image Generative Models understand Ethical Natural
Language Interventions? [67.97752431429865]
We study the effect on the diversity of the generated images when adding ethical intervention.
Preliminary studies indicate that a large change in the model predictions is triggered by certain phrases such as 'irrespective of gender'
arXiv Detail & Related papers (2022-10-27T07:32:39Z) - Markedness in Visual Semantic AI [3.4157048274143316]
We evaluate the state-of-the-art multimodal "visual semantic" model CLIP for biases related to the marking of age, gender, and race or ethnicity.
Female individuals under the age of 20 are more likely than Male individuals to be marked with a gender label, but less likely to be marked with an age label.
As age increases, the self-similarity of representations of Female individuals increases at a higher rate than for Male individuals.
arXiv Detail & Related papers (2022-05-23T15:14:41Z) - Fairness for Image Generation with Uncertain Sensitive Attributes [97.81354305427871]
This work tackles the issue of fairness in the context of generative procedures, such as image super-resolution.
While traditional group fairness definitions are typically defined with respect to specified protected groups, we emphasize that there are no ground truth identities.
We show that the natural extension of demographic parity is strongly dependent on the grouping, and emphimpossible to achieve obliviously.
arXiv Detail & Related papers (2021-06-23T06:17:17Z)
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.