mlsanityData to 7 Oct 2026

MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification

arXiv 2503.12401 ↗First posted 16 Mar 2025cs.CVcited by 1

On the map: Diffusion models → Image generation, text-to-image and editing

also in 1 more
Abstract (arXiv)

Whole Slide Image (WSI) classification poses unique challenges due to the vast image size and numerous non-informative regions, which introduce noise and cause data imbalance during feature aggregation. To address these issues, we propose MExD, an Expert-Infused Diffusion Model that combines the strengths of a Mixture-of-Experts (MoE) mechanism with a diffusion model for enhanced classification. MExD balances patch feature distribution through a novel MoE-based aggregator that selectively emphasizes relevant information, effectively filtering noise, addressing data imbalance, and extracting essential features. These features are then integrated via a diffusion-based generative process to directly yield the class distribution for the WSI. Moving beyond conventional discriminative approaches, MExD represents the first generative strategy in WSI classification, capturing fine-grained details for robust and precise results. Our MExD is validated on three widely-used benchmarks-Camelyon16, TCGA-NSCLC, and BRACS consistently achieving state-of-the-art performance in both binary and multi-class tasks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 40 of its 60 references that are in the map. First posted on arXiv 16 Mar 2025.

Builds on

40 of 60 references.

References · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  4. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  7. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  8. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  9. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  10. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 357
  11. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  12. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 228
28 more
  1. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  2. 2021BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Imagescited by 130
  3. 2020Visual Commonsense R-CNNcited by 106
  4. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  5. 2022CARD: Classification and Regression Diffusion Modelscited by 102
  6. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  7. 2024MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathologycited by 87
  8. 2024Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysiscited by 66
  9. 2024Towards Generalizable Tumor Synthesiscited by 65
  10. 2023Attention-Challenging Multiple Instance Learning for Whole Slide Image Classificationcited by 61
  11. 2024Task-Customized Mixture of Adapters for General Image Fusioncited by 59
  12. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 58
  13. 2022Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentationcited by 55
  14. 2023Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classificationcited by 54
  15. 2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Modelscited by 50
  16. 2023Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learningcited by 47
  17. 2022Differentiable Zooming for Multiple Instance Learning on Whole-Slide Imagescited by 43
  18. 2023The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classificationcited by 41
  19. 2022DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classificationcited by 40
  20. 2023Stochastic Segmentation with Conditional Categorical Diffusion Modelscited by 38
  21. 2024Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledgecited by 35
  22. 2024Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interactioncited by 27
  23. 2021Contextual Dropout: An Efficient Sample-Dependent Dropout Modulecited by 26
  24. 2024MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariantcited by 21
  25. 2022Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalizationcited by 17
  26. 2024Generative Enhancement for 3D Medical Imagescited by 14
  27. 2024Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classificationcited by 12
  28. 2024M4: Multi-Proxy Multi-Gate Mixture of Experts Network for Multiple Instance Learning in Histopathology Image Analysiscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SegMoTE: Token-Level Mixture of Experts for Medical Image Segmentationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2023AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Image
  2. 2024Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
  3. 2025AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification
  4. 2025Diffusion Classifiers Understand Compositionality, but Conditions Apply
  5. 2023Your Diffusion Model is Secretly a Zero-Shot Classifier
  6. 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidance
  7. 2024Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification
  8. 2025All-in-One Slider for Attribute Manipulation in Diffusion Models