Inference Time Debiasing Concepts in Diffusion Models

• URL: http://arxiv.org/abs/2508.14933v1
• Date: Tue, 19 Aug 2025 20:21:02 GMT
• Title: Inference Time Debiasing Concepts in Diffusion Models
• Authors: Lucas S. Kupssinskü, Marco N. Bochernitsan, Jordan Kopper, Otávio Parraga, Rodrigo C. Barros,
• Abstract summary: We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models.<n>It does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based image generation model.<n>We show the effectiveness of the method by debiasing for gender, ethnicity, and age for the concepts of nurse, firefighter, and CEO.
• Score: 1.7802455837461122
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based image generation model. DeCoDi changes the diffusion process to avoid latent dimension regions of biased concepts. While most deep learning debiasing methods require complex or compute-intensive interventions, our method is designed to change only the inference procedure. Therefore, it is more accessible to a wide range of practitioners. We show the effectiveness of the method by debiasing for gender, ethnicity, and age for the concepts of nurse, firefighter, and CEO. Two distinct human evaluators manually inspect 1,200 generated images. Their evaluation results provide evidence that our method is effective in mitigating biases based on gender, ethnicity, and age. We also show that an automatic bias evaluation performed by the GPT4o is not significantly statistically distinct from a human evaluation. Our evaluation shows promising results, with reliable levels of agreement between evaluators and more coverage of protected attributes. Our method has the potential to significantly improve the diversity of images it generates by diffusion-based text-to-image generative models.

Related papers

• FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models [10.857020427374506]
  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.
  arXiv  Detail & Related papers  (2025-10-24T11:47:15Z)
• A Meaningful Perturbation Metric for Evaluating Explainability Methods [55.09730499143998]
  We introduce a novel approach, which harnesses image generation models to perform targeted perturbation.<n> Specifically, we focus on inpainting only the high-relevance pixels of an input image to modify the model's predictions while preserving image fidelity.<n>This is in contrast to existing approaches, which often produce out-of-distribution modifications, leading to unreliable results.
  arXiv  Detail & Related papers  (2025-04-09T11:46:41Z)
• Anisotropic Diffusion Probabilistic Model for Imbalanced Image Classification [8.364943466191933]
  We propose the Anisotropic Diffusion Probabilistic Model (ADPM) for imbalanced image classification problems. We use the data distribution to control the diffusion speed of different class samples during the forward process, effectively improving the classification accuracy of the denoiser in the reverse process. Our results confirm that the anisotropic diffusion model significantly improves the classification accuracy of rare classes while maintaining the accuracy of head classes.
  arXiv  Detail & Related papers  (2024-09-22T04:42:52Z)
• Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models [27.83772742404565]
  We introduce a Prompt-Agnostic Adversarial Perturbation (PAP) method for customized diffusion models. PAP first models the prompt distribution using a Laplace Approximation, and then produces prompt-agnostic perturbations by maximizing a disturbance expectation. This approach effectively tackles the prompt-agnostic attacks, leading to improved defense stability.
  arXiv  Detail & Related papers  (2024-08-20T06:17:56Z)
• On Biases in a UK Biobank-based Retinal Image Classification Model [0.0]
  We explore whether disparities are present in the UK Biobank fundus retinal images by training and evaluating a disease classification model on these images. We find substantial differences despite strong overall performance of the model. We find that these methods are largely unable to enhance fairness, highlighting the need for better bias mitigation methods tailored to the specific type of bias.
  arXiv  Detail & Related papers  (2024-07-30T10:50:07Z)
• Large-scale Reinforcement Learning for Diffusion Models [30.164571425479824]
  Text-to-image diffusion models are susceptible to implicit biases that arise from web-scale text-image training pairs. We present an effective scalable algorithm to improve diffusion models using Reinforcement Learning (RL) We show how our approach substantially outperforms existing methods for aligning diffusion models with human preferences.
  arXiv  Detail & Related papers  (2024-01-20T08:10:43Z)
• Training Diffusion Models with Reinforcement Learning [82.29328477109826]
  Diffusion models are trained with an approximation to the log-likelihood objective. In this paper, we investigate reinforcement learning methods for directly optimizing diffusion models for downstream objectives. We describe how posing denoising as a multi-step decision-making problem enables a class of policy gradient algorithms.
  arXiv  Detail & Related papers  (2023-05-22T17:57:41Z)
• 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)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)
• Deblurring via Stochastic Refinement [85.42730934561101]
  We present an alternative framework for blind deblurring based on conditional diffusion models. Our method is competitive in terms of distortion metrics such as PSNR.
  arXiv  Detail & Related papers  (2021-12-05T04:36:09Z)
• InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics [73.85525896663371]
  This work explores the biases in learning processes based on deep neural network architectures. We employ two gender detection models based on popular deep neural networks. We propose InsideBias, a novel method to detect biased models.
  arXiv  Detail & Related papers  (2020-04-14T15:20:50Z)

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.