mlsanityData to 14 Oct 2026

AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification

arXiv 2406.15303 ↗First posted 18 Jun 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Multiple Instance Learning (MIL) effectively analyzes whole slide images but faces overfitting due to attention over-concentration. While existing solutions rely on complex architectural modifications or additional processing steps, we introduce Attention Entropy Maximization (AEM), a simple yet effective regularization technique. Our investigation reveals the positive correlation between attention entropy and model performance. Building on this insight, we integrate AEM regularization into the MIL framework to penalize excessive attention concentration. To address sensitivity to the AEM weight parameter, we implement Cosine Weight Annealing, reducing parameter dependency. Extensive evaluations demonstrate AEM's superior performance across diverse feature extractors, MIL frameworks, attention mechanisms, and augmentation techniques. Here is our anonymous code: https://github.com/dazhangyu123/AEM.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 42 of its 67 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

42 of 67 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  7. 2020On Layer Normalization in the Transformer Architecturecited by 922
  8. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  9. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  10. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 694
  11. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  12. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
30 more
  1. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
  2. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  3. 2023LongNet: Scaling Transformers to 1,000,000,000 Tokenscited by 204
  4. 2023Quilt-1M: One Million Image-Text Pairs for Histopathologycited by 194
  5. 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
  6. 2023Stabilizing Transformer Training by Preventing Attention Entropy Collapsecited by 161
  7. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 150
  8. 2023Artificial Intelligence for Digital and Computational Pathologycited by 108
  9. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  10. 2021Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classificationcited by 65
  11. 2023Attention-Challenging Multiple Instance Learning for Whole Slide Image Classificationcited by 61
  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. 2021Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imagingcited by 31
  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. 2020Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Explorationcited by 20
  22. 2023HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysiscited by 17
  23. 2022Gigapixel Whole-Slide Images Classification using Locally Supervised Learningcited by 15
  24. 2022MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosiscited by 9
  25. 2023MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysiscited by 9
  26. 2023Multi-Scale Prototypical Transformer for Whole Slide Image Classificationcited by 9
  27. 2021Hybrid Supervision Learning for Pathology Whole Slide Image Classificationcited by 5
  28. 2023Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysiscited by 3
  29. 2023Slot-Mixup with Subsampling: A Simple Regularization for WSI Classificationcited by 3
  30. 2024Multiple Instance Learning with random sampling for Whole Slide Image Classificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 7.

10 papers.

  1. 2024From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classificationcited by 7
  2. 2026ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imagingcited by 6
  3. 2026Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifierscited by 2
  4. 2025Cluster-Level Sparse Multi-Instance Learning for Whole-Slide Imagescited by 0
  5. 2025Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Frameworkcited by 0
  6. 2026Spatial Blindness in Whole-Slide Multiple Instance Learningcited by 0
  7. 2026GCE-MIL: Faithful and Recoverable Evidence for Multiple Instance Learning in Whole-Slide Imagingcited by 0
  8. 2026Normal Guidance is what Attention Needscited by 0
  9. 2026A Multi-Cohort Validation of Censoring-Aware Conformal Lower Predictive Bounds for Pathology Survival Modelscited by 0
  10. 2026Weakly Supervised Spatial Grounding for Discriminative Attention-Based Ultrasound-Histopathology Alignment in Prostate Cancer Gradingcited by 0