mlsanityData to 14 Oct 2026

Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification

arXiv 2307.15254 ↗First posted 28 Jul 2023cs.CV cs.AIcited by 60

Not on the map. Why?

Abstract (arXiv)

The whole slide image (WSI) classification is often formulated as a multiple instance learning (MIL) problem. Since the positive tissue is only a small fraction of the gigapixel WSI, existing MIL methods intuitively focus on identifying salient instances via attention mechanisms. However, this leads to a bias towards easy-to-classify instances while neglecting hard-to-classify instances. Some literature has revealed that hard examples are beneficial for modeling a discriminative boundary accurately. By applying such an idea at the instance level, we elaborate a novel MIL framework with masked hard instance mining (MHIM-MIL), which uses a Siamese structure (Teacher-Student) with a consistency constraint to explore the potential hard instances. With several instance masking strategies based on attention scores, MHIM-MIL employs a momentum teacher to implicitly mine hard instances for training the student model, which can be any attention-based MIL model. This counter-intuitive strategy essentially enables the student to learn a better discriminating boundary. Moreover, the student is used to update the teacher with an exponential moving average (EMA), which in turn identifies new hard instances for subsequent training iterations and stabilizes the optimization. Experimental results on the CAMELYON-16 and TCGA Lung Cancer datasets demonstrate that MHIM-MIL outperforms other latest methods in terms of performance and training cost. The code is available at: https://github.com/DearCaat/MHIM-MIL.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Builds on 27 of its 52 references that are in the map. First posted on arXiv 28 Jul 2023.

Builds on

27 of 52 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  7. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  8. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  9. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  10. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  11. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  12. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
15 more
  1. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  2. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  3. 2019Deep neural network models for computational histopathology: A surveycited by 165
  4. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  5. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 132
  6. 2016Revisiting Multiple Instance Neural Networkscited by 119
  7. 2020Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primarycited by 89
  8. 2019CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentationcited by 73
  9. 2017Class Rectification Hard Mining for Imbalanced Deep Learningcited by 67
  10. 2018Neural Image Compression for Gigapixel Histopathology Image Analysiscited by 65
  11. 2021Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classificationcited by 65
  12. 2019Streaming convolutional neural networks for end-to-end learning with multi-megapixel imagescited by 41
  13. 2018Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detectioncited by 32
  14. 2019Deep Instance-Level Hard Negative Mining Model for Histopathology Imagescited by 12
  15. 2019Learning with Batch-wise Optimal Transport Loss for 3D Shape Recognitioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 20; 2025: 21; 2026: 17.

60 papers.

Sort:

By area:

  1. 2024Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathologycited by 72
  2. 2024Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathologycited by 67
  3. 2023Attention-Challenging Multiple Instance Learning for Whole Slide Image Classificationcited by 61
  4. 2024Transcriptomics-guided Slide Representation Learning in Computational Pathologycited by 51
  5. 2024Masked Image Modeling: A Surveycited by 29
  6. 2025ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classificationcited by 28
  7. 2024Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interactioncited by 27
  8. 2024Vim4Path: Self-Supervised Vision Mamba for Histopathology Imagescited by 19
  9. 2024Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classificationcited by 12
  10. 2024AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classificationcited by 10
  11. 2024Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspectivecited by 10
  12. 2025OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transportcited by 8
38 more
  1. 2024From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classificationcited by 7
  2. 2025How Effective Can Dropout Be in Multiple Instance Learning ?cited by 7
  3. 2024Image Distillation for Safe Data Sharing in Histopathologycited by 6
  4. 2024Prompting Whole Slide Image Based Genetic Biomarker Predictioncited by 6
  5. 2024Computational Pathology for Accurate Prediction of Breast Cancer Recurrence: Development and Validation of a Deep Learning-based Toolcited by 6
  6. 2025Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Studycited by 6
  7. 2026ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imagingcited by 6
  8. 2023Exploiting Facial Relationships and Feature Aggregation for Multi-Face Forgery Detectioncited by 5
  9. 2026Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoningcited by 5
  10. 2024Hard Negative Sample Mining for Whole Slide Image Classificationcited by 4
  11. 2024RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistencycited by 4
  12. 2025MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classificationcited by 3
  13. 2025PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantizationcited by 3
  14. 2025Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysiscited by 3
  15. 2024Fine-tuning a Multiple Instance Learning Feature Extractor with Masked Context Modelling and Knowledge Distillationcited by 2
  16. 2025Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysiscited by 2
  17. 2025Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learningcited by 2
  18. 2026MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarioscited by 2
  19. 2024iMD4GC: Incomplete Multimodal Data Integration to Advance Precise Treatment Response Prediction and Survival Analysis for Gastric Cancercited by 1
  20. 2024Learning Spatial-Preserving Hierarchical Representations for Digital Pathologycited by 1
  21. 2025MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classificationcited by 1
  22. 2025Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysiscited by 1
  23. 2025MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Imagecited by 1
  24. 2026Exploiting Label-Independent Regularization from Spatial Dependencies for Whole Slide Image Analysiscited by 1
  25. 2026MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classificationcited by 1
  26. 2026Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MILcited by 1
  27. 2026QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imagingcited by 1
  28. 2024BAHOP: Similarity-based Basin Hopping for A fast hyper-parameter search in WSI classificationcited by 0
  29. 2024PreMix: Label-Efficient Multiple Instance Learning via Non-Contrastive Pre-training and Feature Mixingcited by 0
  30. 2025A Novel Approach to Linking Histology Images with DNA Methylationcited by 0
  31. 2025Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learningcited by 0
  32. 2025Explainable Depression Detection using Masked Hard Instance Miningcited by 0
  33. 2025PathGene: Benchmarking Driver Gene Mutations and Exon Prediction Using Multicenter Lung Cancer Histopathology Image Datasetcited by 0
  34. 2025Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classificationcited by 0
  35. 2025MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classificationcited by 0
  36. 2025SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 0
  37. 2025Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Frameworkcited by 0
  38. 2025A Hierarchical Geometry-guided Transformer for Histological Subtyping of Primary Liver Cancercited by 0

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher
  2. 2024Distilling High Diagnostic Value Patches for Whole Slide Image Classification Using Attention Mechanism
  3. 2025PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis
  4. 2026Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning
  5. 2024Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification
  6. 2025LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillation
  7. 2025Dual-stream attention-guided learning for weakly supervised whole slide image classification
  8. 2022Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification