T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image
Generation
- URL: http://arxiv.org/abs/2306.00905v1
- Date: Thu, 1 Jun 2023 17:02:51 GMT
- Title: T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image
Generation
- Authors: Jialu Wang, Xinyue Gabby Liu, Zonglin Di, Yang Liu, Xin Eric Wang
- Abstract summary: We propose a novel Text-to-Image Association Test (T2IAT) framework that quantifies the implicit stereotypes between concepts and images.
We replicate the previously documented bias tests on generative models, including morally neutral tests on flowers and insects.
The results of these experiments demonstrate the presence of complex stereotypical behaviors in image generations.
- Score: 11.109588924016254
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Warning: This paper contains several contents that may be toxic, harmful, or
offensive.
In the last few years, text-to-image generative models have gained remarkable
success in generating images with unprecedented quality accompanied by a
breakthrough of inference speed. Despite their rapid progress, human biases
that manifest in the training examples, particularly with regard to common
stereotypical biases, like gender and skin tone, still have been found in these
generative models. In this work, we seek to measure more complex human biases
exist in the task of text-to-image generations. Inspired by the well-known
Implicit Association Test (IAT) from social psychology, we propose a novel
Text-to-Image Association Test (T2IAT) framework that quantifies the implicit
stereotypes between concepts and valence, and those in the images. We replicate
the previously documented bias tests on generative models, including morally
neutral tests on flowers and insects as well as demographic stereotypical tests
on diverse social attributes. The results of these experiments demonstrate the
presence of complex stereotypical behaviors in image generations.
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) - New Job, New Gender? Measuring the Social Bias in Image Generation
Models [88.93677200602887]
Image generation models can generate or edit images from a given text.
Recent advancements in image generation technology, exemplified by DALL-E and Midjourney, have been groundbreaking.
These advanced models are often trained on massive Internet datasets, making them susceptible to generating content that perpetuates social stereotypes and biases.
We propose BiasPainter, a novel testing framework that can accurately, automatically and comprehensively trigger social bias in image generation models.
arXiv Detail & Related papers (2024-01-01T14:06:55Z) - Word-Level Explanations for Analyzing Bias in Text-to-Image Models [72.71184730702086]
Text-to-image (T2I) models can generate images that underrepresent minorities based on race and sex.
This paper investigates which word in the input prompt is responsible for bias in generated images.
arXiv Detail & Related papers (2023-06-03T21:39:07Z) - 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) - A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the
Input is Under-Specified? [7.586041161211335]
We investigate properties of images generated in response to prompts which are visually under-specified.
We find that in many cases, images contain similar demographic biases to those reported in the stereotype literature.
arXiv Detail & Related papers (2023-02-14T16:11:06Z) - 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) - 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) - DALL-Eval: Probing the Reasoning Skills and Social Biases of
Text-to-Image Generation Models [73.12069620086311]
We investigate the visual reasoning capabilities and social biases of text-to-image models.
First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding.
Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images.
arXiv Detail & Related papers (2022-02-08T18:36:52Z)
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.