FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

• URL: http://arxiv.org/abs/2510.21363v1
• Date: Fri, 24 Oct 2025 11:47:15 GMT
• Title: FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
• Authors: Zihao Fu, Ryan Brown, Shun Shao, Kai Rawal, Eoin Delaney, Chris Russell,
• Abstract summary: We introduce FairImagen, a post-hoc debiasing framework that operates on prompt embeddings to mitigate societal biases.<n>Our framework outperforms existing post-hoc methods and offers a simple, scalable, and model-agnostic solution for equitable text-to-image generation.
• Score: 10.857020427374506
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image diffusion models, such as Stable Diffusion, have demonstrated remarkable capabilities in generating high-quality and diverse images from natural language prompts. However, recent studies reveal that these models often replicate and amplify societal biases, particularly along demographic attributes like gender and race. In this paper, we introduce FairImagen (https://github.com/fuzihaofzh/FairImagen), a post-hoc debiasing framework that operates on prompt embeddings to mitigate such biases without retraining or modifying the underlying diffusion model. Our method integrates Fair Principal Component Analysis to project CLIP-based input embeddings into a subspace that minimizes group-specific information while preserving semantic content. We further enhance debiasing effectiveness through empirical noise injection and propose a unified cross-demographic projection method that enables simultaneous debiasing across multiple demographic attributes. Extensive experiments across gender, race, and intersectional settings demonstrate that FairImagen significantly improves fairness with a moderate trade-off in image quality and prompt fidelity. Our framework outperforms existing post-hoc methods and offers a simple, scalable, and model-agnostic solution for equitable text-to-image generation.

Related papers

• A Framework for Benchmarking Fairness-Utility Trade-offs in Text-to-Image Models via Pareto Frontiers [1.6516902135723865]
  We propose a method for evaluating fairness and utility in text-to-image models.<n>Our method outlines all configurations that optimize fairness for a given utility and vice-versa.
  arXiv  Detail & Related papers  (2025-08-22T19:09:22Z)
• Debiasing Vison-Language Models with Text-Only Training [15.069736314663352]
  We propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases. To address the limitations, we propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases.
  arXiv  Detail & Related papers  (2024-10-12T04:34:46Z)
• Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models [0.0]
  Text-to-Image (TTI) systems have come under increased scrutiny for social biases. We investigate embedding spaces as a source of bias for TTI models. We find that biased multimodal embeddings like CLIP can result in lower alignment scores for representationally balanced TTI models.
  arXiv  Detail & Related papers  (2024-09-15T01:09:55Z)
• Coherent and Multi-modality Image Inpainting via Latent Space Optimization [61.99406669027195]
  PILOT (intextbfPainting vtextbfIa textbfLatent textbfOptextbfTimization) is an optimization approach grounded on a novel textitsemantic centralization and textitbackground preservation loss. Our method searches latent spaces capable of generating inpainted regions that exhibit high fidelity to user-provided prompts while maintaining coherence with the background.
  arXiv  Detail & Related papers  (2024-07-10T19:58:04Z)
• 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)
• Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers [120.49126407479717]
  This paper explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR) We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap between sketches and photos.
  arXiv  Detail & Related papers  (2024-03-12T00:02:03Z)
• Benchmarking the Fairness of Image Upsampling Methods [29.01986714656294]
  We develop a set of metrics for performance and fairness of conditional generative models. We benchmark their imbalances and diversity. As part of the study, a subset of datasets replicates the racial distribution of common-scale face.
  arXiv  Detail & Related papers  (2024-01-24T16:13:26Z)
• Fair Text-to-Image Diffusion via Fair Mapping [32.02815667307623]
  We propose a flexible, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image diffusion model. By effectively addressing the issue of implicit language bias, our method produces more fair and diverse image outputs.
  arXiv  Detail & Related papers  (2023-11-29T15:02:01Z)
• DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability [75.9781362556431]
  We propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. We show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks.
  arXiv  Detail & Related papers  (2023-08-18T05:03:48Z)
• Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners [88.07317175639226]
  We propose a novel approach, Discriminative Stable Diffusion (DSD), which turns pre-trained text-to-image diffusion models into few-shot discriminative learners. Our approach mainly uses the cross-attention score of a Stable Diffusion model to capture the mutual influence between visual and textual information.
  arXiv  Detail & Related papers  (2023-05-18T05:41:36Z)
• Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
  We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification. Our generative approach to classification attains strong results on a variety of benchmarks. Our results are a step toward using generative over discriminative models for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T17:59:56Z)
• 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)

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.