TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models
- URL: http://arxiv.org/abs/2312.01261v2
- Date: Wed, 17 Jul 2024 02:15:51 GMT
- Title: TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models
- Authors: Aditya Chinchure, Pushkar Shukla, Gaurav Bhatt, Kiri Salij, Kartik Hosanagar, Leonid Sigal, Matthew Turk,
- Abstract summary: We propose a general approach to study and quantify a broad spectrum of biases, for any TTI model and for any prompt.
Our approach automatically identifies potential biases that might be relevant to the given prompt, and measures those biases.
We show that our method is uniquely capable of explaining complex multi-dimensional biases through semantic concepts.
- Score: 22.076898042211305
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Text-to-Image (TTI) generative models have shown great progress in the past few years in terms of their ability to generate complex and high-quality imagery. At the same time, these models have been shown to suffer from harmful biases, including exaggerated societal biases (e.g., gender, ethnicity), as well as incidental correlations that limit such a model's ability to generate more diverse imagery. In this paper, we propose a general approach to study and quantify a broad spectrum of biases, for any TTI model and for any prompt, using counterfactual reasoning. Unlike other works that evaluate generated images on a predefined set of bias axes, our approach automatically identifies potential biases that might be relevant to the given prompt, and measures those biases. In addition, we complement quantitative scores with post-hoc explanations in terms of semantic concepts in the images generated. We show that our method is uniquely capable of explaining complex multi-dimensional biases through semantic concepts, as well as the intersectionality between different biases for any given prompt. We perform extensive user studies to illustrate that the results of our method and analysis are consistent with human judgements.
Related papers
- On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [49.60774626839712]
multimodal generative models have sparked critical discussions on their fairness, reliability, and potential for misuse.
We propose an evaluation framework designed to assess model reliability through their responses to perturbations in the embedding space.
Our method lays the groundwork for detecting unreliable, bias-injected models and retrieval of bias provenance.
arXiv Detail & Related papers (2024-11-21T09:46:55Z) - GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models [75.04426753720553]
We propose a framework to identify, quantify, and explain biases in an open set setting.
This pipeline leverages a Large Language Model (LLM) to propose biases starting from a set of captions.
We show two variations of this framework: OpenBias and GradBias.
arXiv Detail & Related papers (2024-08-29T16:51:07Z) - Gender Bias Evaluation in Text-to-image Generation: A Survey [25.702257177921048]
We review recent work on gender bias evaluation in text-to-image generation.
We focus on the evaluation of recent popular models such as Stable Diffusion and DALL-E 2.
arXiv Detail & Related papers (2024-08-21T06:01:23Z) - Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models [0.0]
Despite advances in generative models, most studies ignore the presence of bias.
In this paper, we examine several text-to-image models not only by qualitatively assessing their performance in generating accurate images of human faces, groups, and specified numbers of objects but also by presenting a social bias analysis.
As expected, models with larger capacity generate higher-quality images. However, we also document the inherent gender or social biases these models possess, offering a more complete understanding of their impact and limitations.
arXiv Detail & Related papers (2024-06-28T14:10:42Z) - DiffusionPID: Interpreting Diffusion via Partial Information Decomposition [24.83767778658948]
We apply information-theoretic principles to decompose the input text prompt into its elementary components.
We analyze how individual tokens and their interactions shape the generated image.
We show that PID is a potent tool for evaluating and diagnosing text-to-image diffusion models.
arXiv Detail & Related papers (2024-06-07T18:17:17Z) - MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models [3.3454373538792552]
We introduce a method that addresses intersectional bias in diffusion-based text-to-image models by modifying cross-attention maps in a disentangled manner.
Our approach utilizes a pre-trained Stable Diffusion model, eliminates the need for an additional set of reference images, and preserves the original quality for unaltered concepts.
arXiv Detail & Related papers (2024-03-28T17:54:38Z) - Quantifying Bias in Text-to-Image Generative Models [49.60774626839712]
Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas.
Existing T2I model bias evaluation methods only focus on social biases.
We propose an evaluation methodology to quantify general biases in T2I generative models, without any preconceived notions.
arXiv Detail & Related papers (2023-12-20T14:26:54Z) - ITI-GEN: Inclusive Text-to-Image Generation [56.72212367905351]
This study investigates inclusive text-to-image generative models that generate images based on human-written prompts.
We show that, for some attributes, images can represent concepts more expressively than text.
We propose a novel approach, ITI-GEN, that leverages readily available reference images for Inclusive Text-to-Image GENeration.
arXiv Detail & Related papers (2023-09-11T15:54:30Z) - 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) - Unravelling the Effect of Image Distortions for Biased Prediction of
Pre-trained Face Recognition Models [86.79402670904338]
We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions.
We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
arXiv Detail & Related papers (2021-08-14T16:49:05Z)
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.