Text-to-Image Representativity Fairness Evaluation Framework

• URL: http://arxiv.org/abs/2410.14201v1
• Date: Fri, 18 Oct 2024 06:31:57 GMT
• Title: Text-to-Image Representativity Fairness Evaluation Framework
• Authors: Asma Yamani, Malak Baslyman,
• Abstract summary: We propose Text-to-Image (TTI) Representativity Fairness Evaluation Framework. In this framework, we evaluate three aspects of a TTI system; diversity, inclusion, and quality. The evaluation of our framework on Stable Diffusion shows that the framework can effectively capture the bias in TTI systems.
• Score: 0.42970700836450487
• License:
• Abstract: Text-to-Image generative systems are progressing rapidly to be a source of advertisement and media and could soon serve as image searches or artists. However, there is a significant concern about the representativity bias these models embody and how these biases can propagate in the social fabric after fine-tuning them. Therefore, continuously monitoring and evaluating these models for fairness is important. To address this issue, we propose Text-to-Image (TTI) Representativity Fairness Evaluation Framework. In this framework, we evaluate three aspects of a TTI system; diversity, inclusion, and quality. For each aspect, human-based and model-based approaches are proposed and evaluated for their ability to capture the bias and whether they can substitute each other. The framework starts by suggesting the prompts for generating the images for the evaluation based on the context and the sensitive attributes under study. Then the three aspects are evaluated using the proposed approaches. Based on the evaluation, a decision is made regarding the representativity bias within the TTI system. The evaluation of our framework on Stable Diffusion shows that the framework can effectively capture the bias in TTI systems. The results also confirm that our proposed model based-approaches can substitute human-based approaches in three out of four components with high correlation, which could potentially reduce costs and automate the process. The study suggests that continual learning of the model on more inclusive data across disadvantaged minorities such as Indians and Middle Easterners is essential to mitigate current stereotyping and lack of inclusiveness.

Related papers

• Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models [16.60455968933097]
  Concept erasure methods can inadvertently generate NSFW content even with efforts on filtering NSFW content from the training dataset. We present the first systematic investigation of concept erasure methods for NSFW content and its sub-themes in text-to-image diffusion models. We provide a holistic evaluation of 11 state-of-the-art baseline methods with 14 variants.
  arXiv  Detail & Related papers  (2025-02-18T04:25:42Z)
• INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models [8.340794604348632]
  Multi-modal AI systems have potential for industrial applications by emulating human-like cognition. They also pose significant ethical challenges, including amplifying harmful content and reinforcing societal biases. This paper presents INFELM, an in-depth fairness evaluation on widely-used text-to-image models.
  arXiv  Detail & Related papers  (2024-12-28T02:28:19Z)
• Multimodal Approaches to Fair Image Classification: An Ethical Perspective [0.0]
  This thesis explores the intersection of technology and ethics in the development of fair image classification models. I focus on improving fairness and methods of using multiple modalities to combat harmful demographic bias. The study critically examines existing biases in image datasets and classification algorithms, proposes innovative methods for mitigating these biases, and evaluates the ethical implications of deploying such systems in real-world scenarios.
  arXiv  Detail & Related papers  (2024-12-11T19:58:31Z)
• 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)
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
  Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
  arXiv  Detail & Related papers  (2024-06-21T03:58:44Z)
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Gender Biases in Automatic Evaluation Metrics for Image Captioning [87.15170977240643]
  We conduct a systematic study of gender biases in model-based evaluation metrics for image captioning tasks. We demonstrate the negative consequences of using these biased metrics, including the inability to differentiate between biased and unbiased generations. We present a simple and effective way to mitigate the metric bias without hurting the correlations with human judgments.
  arXiv  Detail & Related papers  (2023-05-24T04:27:40Z)
• 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)

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.