mlsanityData to 7 Oct 2026

FairDiffusion: Enhancing Equity in Latent Diffusion Models via Fair Bayesian Perturbation

arXiv 2412.20374 ↗First posted 29 Dec 2024cs.CV cs.LGcited by 4

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Recent progress in generative AI, especially diffusion models, has demonstrated significant utility in text-to-image synthesis. Particularly in healthcare, these models offer immense potential in generating synthetic datasets and training medical students. However, despite these strong performances, it remains uncertain if the image generation quality is consistent across different demographic subgroups. To address this critical concern, we present the first comprehensive study on the fairness of medical text-to-image diffusion models. Our extensive evaluations of the popular Stable Diffusion model reveal significant disparities across gender, race, and ethnicity. To mitigate these biases, we introduce FairDiffusion, an equity-aware latent diffusion model that enhances fairness in both image generation quality as well as the semantic correlation of clinical features. In addition, we also design and curate FairGenMed, the first dataset for studying the fairness of medical generative models. Complementing this effort, we further evaluate FairDiffusion on two widely-used external medical datasets: HAM10000 (dermatoscopic images) and CheXpert (chest X-rays) to demonstrate FairDiffusion's effectiveness in addressing fairness concerns across diverse medical imaging modalities. Together, FairDiffusion and FairGenMed significantly advance research in fair generative learning, promoting equitable benefits of generative AI in healthcare.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 41 of its 69 references that are in the map. First posted on arXiv 29 Dec 2024.

Builds on

41 of 69 references.

Closest ancestors · 9

Same direction, newest first

  1. 2022Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation7 Nov
  2. 2022Generation of Anonymous Chest Radiographs Using Latent Diffusion Models for Training Thoracic Abnormality Classification Systems2 Nov
  3. 2022Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains9 Oct
  4. 2022Brain Imaging Generation with Latent Diffusion Models15 Sep
  5. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Models17 Jul
  6. 2022Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction5 Mar
  7. 2022Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic Model27 Jan
  8. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov
  9. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  9. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  10. 2019An Introduction to Variational Autoencoderscited by 997
  11. 2018Self-Attention Generative Adversarial Networkscited by 809
  12. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
20 more
  1. 2019PadChest: A large chest x-ray image dataset with multi-label annotated reportscited by 308
  2. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  3. 2016Coupled Generative Adversarial Networkscited by 216
  4. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  5. 2021Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Datasetcited by 184
  6. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  7. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 121
  8. 2022Protein structure generation via folding diffusioncited by 113
  9. 2023Generative models improve fairness of medical classifiers under distribution shiftscited by 90
  10. 2023Finetuning Text-to-Image Diffusion Models for Fairnesscited by 90
  11. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  12. 2023Quantum circuit synthesis with diffusion modelscited by 33
  13. 2022Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Reviewcited by 27
  14. 2024FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classificationcited by 19
  15. 2023Harvard Glaucoma Detection and Progression: A Multimodal Multitask Dataset and Generalization-Reinforced Semi-Supervised Learningcited by 17
  16. 2023FairVision: Equitable Deep Learning for Eye Disease Screening via Fair Identity Scalingcited by 13
  17. 2022Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learningcited by 11
  18. 2023Maximum diffusion reinforcement learningcited by 8
  19. 2022Discriminative Kernel Convolution Network for Multi-Label Ophthalmic Disease Detection on Imbalanced Fundus Image Datasetcited by 6
  20. 2023FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scalingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRAcited by 1
  2. 2025GANDiff FR: Hybrid GAN Diffusion Synthesis for Causal Bias Attribution in Face Recognitioncited by 0
  3. 2026FairGen: Preference-Aligned Diffusion for Demographically Equitable Medical Image Synthesiscited by 0
  4. 2026A radiographic world model for clinical reasoning and evidence generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024FairSkin: Fair Diffusion for Skin Disease Image Generation
  2. 2024FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions
  3. 2023Fair Text-to-Image Diffusion via Fair Mapping
  4. 2025FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance
  5. 2024Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
  6. 2025Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image Generation
  7. 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
  8. 2025Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data