Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis
Not on the map. Why?
Abstract (arXiv)
Digitizing pathological images into gigapixel Whole Slide Images (WSIs) has opened new avenues for Computational Pathology (CPath). As positive tissue comprises only a small fraction of gigapixel WSIs, existing Multiple Instance Learning (MIL) methods typically focus on identifying salient instances via attention mechanisms. However, this leads to a bias towards easy-to-classify instances while neglecting challenging ones. Recent studies have shown that hard examples are crucial for accurately modeling discriminative boundaries. Applying such an idea at the instance level, we elaborate a novel MIL framework with masked hard instance mining (MHIM-MIL), which utilizes a Siamese structure with a consistency constraint to explore the hard instances. Using a class-aware instance probability, MHIM-MIL employs a momentum teacher to mask salient instances and implicitly mine hard instances for training the student model. To obtain diverse, non-redundant hard instances, we adopt large-scale random masking while utilizing a global recycle network to mitigate the risk of losing key features. Furthermore, the student updates the teacher using an exponential moving average, which identifies new hard instances for subsequent training iterations and stabilizes optimization. Experimental results on cancer diagnosis, subtyping, survival analysis tasks, and 12 benchmarks demonstrate that MHIM-MIL outperforms the latest methods in both performance and efficiency. The code is available at: https://github.com/DearCaat/MHIM-MIL.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 57 of its 100 references that are in the map. First posted on arXiv 15 Sep 2025.
Builds on
57 of 100 references.
References · 57
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
- 2014DeepWalk: Online Learning of Social Representationscited by 1,547
- 2018Attention-based Deep Multiple Instance Learningcited by 1,095
- 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
- 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
- 2015LINE: Large-scale Information Network Embeddingcited by 582
- 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
- 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
38 more
- 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
- 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
- 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
- 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
- 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
- 2019Pathomic Fusion: An Integrated Framework for Fusing Histopathology and Genomic Features for Cancer Diagnosis and Prognosiscited by 165
- 2019Deep neural network models for computational histopathology: A surveycited by 165
- 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
- 2016Revisiting Multiple Instance Neural Networkscited by 119
- 2023Artificial Intelligence for Digital and Computational Pathologycited by 108
- 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
- 2020Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primarycited by 89
- 2024MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathologycited by 88
- 2019CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentationcited by 73
- 2024Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathologycited by 72
- 2023Cross-Modal Translation and Alignment for Survival Analysiscited by 70
- 2017Class Rectification Hard Mining for Imbalanced Deep Learningcited by 67
- 2024Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathologycited by 67
- 2024Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysiscited by 67
- 2021Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classificationcited by 65
- 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 60
- 2024A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Modelcited by 59
- 2024Transcriptomics-guided Slide Representation Learning in Computational Pathologycited by 51
- 2024Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillationcited by 43
- 2019Streaming convolutional neural networks for end-to-end learning with multi-megapixel imagescited by 41
- 2018Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detectioncited by 32
- 2025ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classificationcited by 28
- 2024Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interactioncited by 27
- 2023Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Miningcited by 25
- 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Needcited by 22
- 2024Vim4Path: Self-Supervised Vision Mamba for Histopathology Imagescited by 19
- 2023AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Imagescited by 18
- 2023Accelerating Neural Field Training via Soft Miningcited by 15
- 2024Does Negative Sampling Matter? A Review with Insights into its Theory and Applicationscited by 15
- 2019Deep Instance-Level Hard Negative Mining Model for Histopathology Imagescited by 12
- 2024Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classificationcited by 12
- 2023Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learningcited by 9
- 2023Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identificationcited by 9
50 most cited of 57 All 57 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.