mlsanityData to 14 Oct 2026

Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification

arXiv 2311.07125 ↗First posted 13 Nov 2023cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

In the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) classification, attention mechanisms often focus on a subset of discriminative instances, which are closely linked to overfitting. To mitigate overfitting, we present Attention-Challenging MIL (ACMIL). ACMIL combines two techniques based on separate analyses for attention value concentration. Firstly, UMAP of instance features reveals various patterns among discriminative instances, with existing attention mechanisms capturing only some of them. To remedy this, we introduce Multiple Branch Attention (MBA) to capture more discriminative instances using multiple attention branches. Secondly, the examination of the cumulative value of Top-K attention scores indicates that a tiny number of instances dominate the majority of attention. In response, we present Stochastic Top-K Instance Masking (STKIM), which masks out a portion of instances with Top-K attention values and allocates their attention values to the remaining instances. The extensive experimental results on three WSI datasets with two pre-trained backbones reveal that our ACMIL outperforms state-of-the-art methods. Additionally, through heatmap visualization and UMAP visualization, this paper extensively illustrates ACMIL's effectiveness in suppressing attention value concentration and overcoming the overfitting challenge. The source code is available at urlhttps://github.com/dazhangyu123/ACMIL.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 13 Nov 2023.

Builds on

38 of 72 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  7. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  8. 2017Random Erasing Data Augmentationcited by 1,239
  9. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  10. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  11. 2016Language Modeling with Gated Convolutional Networkscited by 702
  12. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
26 more
  1. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  2. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  3. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
  4. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  5. 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
  6. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  7. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 150
  8. 2021BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Imagescited by 132
  9. 2016Deep Learning for Identifying Metastatic Breast Cancercited by 93
  10. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  11. 2018Neural Image Compression for Gigapixel Histopathology Image Analysiscited by 65
  12. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 60
  13. 2023Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classificationcited by 54
  14. 2023Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learningcited by 47
  15. 2020Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histologycited by 43
  16. 2022Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classificationcited by 43
  17. 2019Streaming convolutional neural networks for end-to-end learning with multi-megapixel imagescited by 41
  18. 2022ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classificationcited by 30
  19. 2023Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classificationcited by 27
  20. 2022Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathologycited by 26
  21. 2020Predicting molecular phenotypes from histopathology images: a transcriptome-wide expression-morphology analysis in breast cancercited by 21
  22. 2018Cancer Metastasis Detection With Neural Conditional Random Fieldcited by 17
  23. 2021Efficient Classification of Very Large Images with Tiny Objectscited by 17
  24. 2022Iterative Patch Selection for High-Resolution Image Recognitioncited by 14
  25. 2023Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classificationcited by 8
  26. 2023Dual-Query Multiple Instance Learning for Dynamic Meta-Embedding based Tumor Classificationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 13; 2025: 25; 2026: 21.

61 papers.

Sort:

By area:

  1. 2025CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logiccited by 29
  2. 2024PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaborationcited by 28
  3. 2024HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classificationcited by 13
  4. 2023Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classificationcited by 12
  5. 2024Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysiscited by 12
  6. 2024AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classificationcited by 10
  7. 2024From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classificationcited by 7
  8. 2025Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathologycited by 6
  9. 2025Efficient Whole Slide Pathology VQA via Token Compressioncited by 6
  10. 2025LoC-Path: Learning to Compress for Pathology Multimodal Large Language Modelscited by 6
  11. 2026ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imagingcited by 6
  12. 2026Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoningcited by 5
38 more
  1. 2024RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistencycited by 4
  2. 2023Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysiscited by 3
  3. 2025Can We Simplify Slide-level Fine-tuning of Pathology Foundation Models?cited by 3
  4. 2025PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantizationcited by 3
  5. 2025Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysiscited by 3
  6. 2024Biochemical Prostate Cancer Recurrence Prediction: Thinking Fast & Slowcited by 2
  7. 2025HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysiscited by 2
  8. 2025Sequential Attention-based Sampling for Histopathological Analysiscited by 2
  9. 2024Beyond accuracy: quantifying the reliability of Multiple Instance Learning for Whole Slide Image classificationcited by 1
  10. 2024Beyond Labels: A Self-Supervised Framework with Masked Autoencoders and Random Cropping for Breast Cancer Subtype Classificationcited by 1
  11. 2025MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classificationcited by 1
  12. 2025SMILE: a Scale-aware Multiple Instance Learning Method for Multicenter STAS Lung Cancer Histopathology Diagnosiscited by 1
  13. 2025Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imagingcited by 1
  14. 2025SlideMamba: Entropy-Based Adaptive Fusion of GNN and Mamba for Enhanced Representation Learning in Digital Pathologycited by 1
  15. 2025MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classificationcited by 1
  16. 2026A Deployment-Friendly Foundational Framework for Efficient Computational Pathologycited by 1
  17. 2026Exploiting Label-Independent Regularization from Spatial Dependencies for Whole Slide Image Analysiscited by 1
  18. 2026Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MILcited by 1
  19. 2026QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imagingcited by 1
  20. 2024MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Imagescited by 0
  21. 2024Efficient Whole Slide Image Classification through Fisher Vector Representationcited by 0
  22. 2024Multimodal Outer Arithmetic Block Dual Fusion of Whole Slide Images and Omics Data for Precision Oncologycited by 0
  23. 2024On the Generalizability of Iterative Patch Selection for Memory-Efficient High-Resolution Image Classificationcited by 0
  24. 2025LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillationcited by 0
  25. 2025Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learningcited by 0
  26. 2025DLiPath: A Benchmark for the Comprehensive Assessment of Donor Liver Based on Histopathological Image Datasetcited by 0
  27. 2025Reducing Variability of Multiple Instance Learning Methods for Digital Pathologycited by 0
  28. 2025Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classificationcited by 0
  29. 2025Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Frameworkcited by 0
  30. 2025A Hierarchical Geometry-guided Transformer for Histological Subtyping of Primary Liver Cancercited by 0
  31. 2025Fourier Transform Multiple Instance Learning for Whole Slide Image Classificationcited by 0
  32. 2025Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representationcited by 0
  33. 2025Cross-Stain Contrastive Learning for Paired Immunohistochemistry and Histopathology Slide Representation Learningcited by 0
  34. 2025CAPRMIL: Context-Aware Patch Representations for Multiple Instance Learningcited by 0
  35. 2026Prototype Instance-semantic Disentanglement with Low-rank Regularized Subspace Clustering for WSIs Explainable Recognitioncited by 0
  36. 2026MacNet: An End-to-End Manifold-Constrained Adaptive Clustering Network for Interpretable Whole Slide Image Classificationcited by 0
  37. 2026AINet: Anchor Instances Learning for Regional Heterogeneity in Whole Slide Imagecited by 0
  38. 2026Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysiscited by 0

50 most cited of 61 All 61 (JSON)