mlsanityData to 7 Oct 2026

Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification

arXiv 2403.07939 ↗First posted 9 Mar 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Multi-Instance Learning (MIL) has shown impressive performance for histopathology whole slide image (WSI) analysis using bags or pseudo-bags. It involves instance sampling, feature representation, and decision-making. However, existing MIL-based technologies at least suffer from one or more of the following problems: 1) requiring high storage and intensive pre-processing for numerous instances (sampling); 2) potential over-fitting with limited knowledge to predict bag labels (feature representation); 3) pseudo-bag counts and prior biases affect model robustness and generalizability (decision-making). Inspired by clinical diagnostics, using the past sampling instances can facilitate the final WSI analysis, but it is barely explored in prior technologies. To break free these limitations, we integrate the dynamic instance sampling and reinforcement learning into a unified framework to improve the instance selection and feature aggregation, forming a novel Dynamic Policy Instance Selection (DPIS) scheme for better and more credible decision-making. Specifically, the measurement of feature distance and reward function are employed to boost continuous instance sampling. To alleviate the over-fitting, we explore the latent global relations among instances for more robust and discriminative feature representation while establishing reward and punishment mechanisms to correct biases in pseudo-bags using contrastive learning. These strategies form the final Dynamic Policy-Driven Adaptive Multi-Instance Learning (PAMIL) method for WSI tasks. Extensive experiments reveal that our PAMIL method outperforms the state-of-the-art by 3.8% on CAMELYON16 and 4.4% on TCGA lung cancer datasets.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 9 Mar 2024.

Builds on

29 of 45 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  7. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  8. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  9. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  10. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  11. 2021Reinforcement learning based recommender systems: A surveycited by 187
  12. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
17 more
  1. 2020Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Imagescited by 81
  2. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 58
  3. 2017Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Trainingcited by 57
  4. 2023Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classificationcited by 54
  5. 2023Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learningcited by 47
  6. 2019Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learningcited by 41
  7. 2022DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classificationcited by 40
  8. 2022ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classificationcited by 30
  9. 2023Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classificationcited by 27
  10. 2018Cancer Metastasis Detection With Neural Conditional Random Fieldcited by 17
  11. 2020Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentationcited by 16
  12. 2022Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directionscited by 15
  13. 2019Learning Where to See: A Novel Attention Model for Automated Immunohistochemical Scoringcited by 14
  14. 2022RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learningcited by 8
  15. 2018Partial Policy-based Reinforcement Learning for Anatomical Landmark Localization in 3D Medical Imagescited by 6
  16. 2023Multi-level Multiple Instance Learning with Transformer for Whole Slide Image Classificationcited by 6
  17. 2023ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classificationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 4.

12 papers.

  1. 2024Frequency-Assisted Mamba for Remote Sensing Image Super-Resolutioncited by 47
  2. 2025How Effective Can Dropout Be in Multiple Instance Learning ?cited by 7
  3. 2025Sequential Attention-based Sampling for Histopathological Analysiscited by 2
  4. 2025MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classificationcited by 1
  5. 2025Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysiscited by 1
  6. 2025Identifying actionable driver mutations in lung cancer using an efficient Asymmetric Transformer Decodercited by 0
  7. 2025Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Predictioncited by 0
  8. 2025DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysiscited by 0
  9. 2026AINet: Anchor Instances Learning for Regional Heterogeneity in Whole Slide Imagecited by 0
  10. 2026A deep learning pipeline for PAM50 subtype classification using histopathology images and multi-objective patch selectioncited by 0
  11. 2026The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignmentcited by 0
  12. 2026CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classificationcited by 0