OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
- URL: http://arxiv.org/abs/2404.07990v1
- Date: Thu, 11 Apr 2024 17:59:56 GMT
- Title: OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
- Authors: Moreno D'IncĂ , Elia Peruzzo, Massimiliano Mancini, Dejia Xu, Vidit Goel, Xingqian Xu, Zhangyang Wang, Humphrey Shi, Nicu Sebe,
- Abstract summary: We tackle the challenge of open-set bias detection in text-to-image generative models presenting OpenBias.
OpenBias identifies and quantifies the severity of biases agnostically, without access to any precompiled set.
We study the behavior of Stable Diffusion 1.5, 2, and XL emphasizing new biases, never investigated before.
- Score: 108.2219657433884
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Text-to-image generative models are becoming increasingly popular and accessible to the general public. As these models see large-scale deployments, it is necessary to deeply investigate their safety and fairness to not disseminate and perpetuate any kind of biases. However, existing works focus on detecting closed sets of biases defined a priori, limiting the studies to well-known concepts. In this paper, we tackle the challenge of open-set bias detection in text-to-image generative models presenting OpenBias, a new pipeline that identifies and quantifies the severity of biases agnostically, without access to any precompiled set. OpenBias has three stages. In the first phase, we leverage a Large Language Model (LLM) to propose biases given a set of captions. Secondly, the target generative model produces images using the same set of captions. Lastly, a Vision Question Answering model recognizes the presence and extent of the previously proposed biases. We study the behavior of Stable Diffusion 1.5, 2, and XL emphasizing new biases, never investigated before. Via quantitative experiments, we demonstrate that OpenBias agrees with current closed-set bias detection methods and human judgement.
Related papers
- VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model [72.13121434085116]
VLBiasBench is a benchmark aimed at evaluating biases in Large Vision-Language Models (LVLMs)
We construct a dataset encompassing nine distinct categories of social biases, including age, disability status, gender, nationality, physical appearance, race, religion, profession, social economic status and two intersectional bias categories (race x gender, and race x social economic status)
We conduct extensive evaluations on 15 open-source models as well as one advanced closed-source model, providing some new insights into the biases revealing from these models.
arXiv Detail & Related papers (2024-06-20T10:56:59Z) - 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) - Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding.
We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
arXiv Detail & Related papers (2023-01-31T20:09:33Z) - Discovering and Mitigating Visual Biases through Keyword Explanation [66.71792624377069]
We propose the Bias-to-Text (B2T) framework, which interprets visual biases as keywords.
B2T can identify known biases, such as gender bias in CelebA, background bias in Waterbirds, and distribution shifts in ImageNet-R/C.
B2T uncovers novel biases in larger datasets, such as Dollar Street and ImageNet.
arXiv Detail & Related papers (2023-01-26T13:58:46Z) - Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data
via Generative Bias-transformation [31.944147533327058]
Contrastive Debiasing via Generative Bias-transformation (CDvG)
We propose a novel method, Contrastive Debiasing via Generative Bias-transformation (CDvG), which works without explicit bias labels or bias-free samples.
Our method demonstrates superior performance compared to prior approaches, especially when bias-free samples are scarce or absent.
arXiv Detail & Related papers (2021-12-02T07:16:06Z) - Don't Discard All the Biased Instances: Investigating a Core Assumption
in Dataset Bias Mitigation Techniques [19.252319300590656]
Existing techniques for mitigating dataset bias often leverage a biased model to identify biased instances.
The role of these biased instances is then reduced during the training of the main model to enhance its robustness to out-of-distribution data.
In this paper, we show that this assumption does not hold in general.
arXiv Detail & Related papers (2021-09-01T10:25:46Z) - BiaSwap: Removing dataset bias with bias-tailored swapping augmentation [20.149645246997668]
Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution.
This paper proposes a novel bias-tailored augmentation-based approach, BiaSwap, for learning debiased representation without requiring supervision on the bias type.
arXiv Detail & Related papers (2021-08-23T08:35:26Z) - Greedy Gradient Ensemble for Robust Visual Question Answering [163.65789778416172]
We stress the language bias in Visual Question Answering (VQA) that comes from two aspects, i.e., distribution bias and shortcut bias.
We propose a new de-bias framework, Greedy Gradient Ensemble (GGE), which combines multiple biased models for unbiased base model learning.
GGE forces the biased models to over-fit the biased data distribution in priority, thus makes the base model pay more attention to examples that are hard to solve by biased models.
arXiv Detail & Related papers (2021-07-27T08:02:49Z)
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.