Multiple Instance Learning

Also known as MIL

Overview

Multiple Instance Learning (MIL) treats an example as a bag of instances and learns to predict from the bag when the informative regions or moments are unknown. It is useful for tasks with labels for whole slides, scans, videos, or documents but few or no labels for individual patches, slices, frames, or passages. Methods range from mean and max pooling to attention, transformers, graphs, and state-space models, often combined with pretrained features, spatial or temporal structure, prototypes, contrastive learning, and pseudo-labels. A central tension is that strong bag-level predictions do not guarantee faithful instance-level evidence, and more complex aggregators do not always outperform simple pooling.

Latest papers

CardsList

104 papers13 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology

    Jun 4, 2026Yanqing Luo, Julius Hense, Niklas Prenißl +4Computational PathologyExplainable Medical Image Analysis

  2. Normal Guidance is what Attention Needs

    May 26, 2026Ethan Harvey, Dennis Johan Loevlie, Michael C. HughesHealthcare3D Medical Imaging

  3. Spatial Blindness in Whole-Slide Multiple Instance Learning

    May 17, 2026Xiangyu Li, Ran SuHistopathology Image ClassificationMultiple Instance Learning

  4. Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MIL

    May 12, 2026Hyun Do Jung, Jungwon Choi, Soojung Choi +2Explainable Medical Image AnalysisHistopathology Image Classification

  5. Bridging the Modality Bottleneck in Pathology MIL through Molecularly Guided Feature Adaptation

    May 12, 2026Yucheng Xing, Pei Liu, Jingying Ma +6Computational PathologyCross-Modal Representation Learning

  6. Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation

    May 9, 2026Yutszyuk Wong, Wentai Wu, Yuen-Ying Yeung +1Online Anomaly DetectionAnomaly Localization

  7. BatMIL: Geometry-Embedding State Space Model for Whole-Slide Image Representation

    May 6, 2026Enhui Chai, Sicheng Chen, Tianyi Zhang +4Histopathology Image ClassificationMultiple Instance Learning

  8. A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification

    Apr 29, 2026Ethan Harvey, Dennis Johan Loevlie, Amir Ali Satani +33D ViTsConvolutional Neural Networks

  9. Validation of Whole-Slide Foundation Models for Image Retrieval in TCGA Data

    Apr 28, 2026Tianhao Lei, Parsa Esmaeilkhani, Saghir Alfasly +5Pathology Foundation ModelsOncology

  10. Hierarchical Prototype-based Domain Priors for Multiple Instance Learning in Multimodal Histopathology Analysis

    Apr 27, 2026Xuemei Qiu, Dawei Fan, Yebin Huang +2Cross-Modal AlignmentPrototype Learning

  11. Weakly Supervised Multicenter Nancy Index Scoring in Ulcerative Colitis Using Foundation Models

    Apr 26, 2026Adam Kukučka, Ondřej Fabián, Vít Musil +1Computational PathologyPathology Foundation Models

  12. Attention-based multiple instance learning for predominant growth pattern prediction in lung adenocarcinoma wsi using foundation models

    Apr 23, 2026Laura Valeria Perez-Herrera, M. J. Garcia-Gonzalez, Karen Lopez-LinaresComputational PathologyPathology Foundation Models

  13. Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images

    Apr 22, 2026Joakim Nguyen, Jian Yu, Jinrui Fang +7Pathology Foundation ModelsMedical Image Classification

  14. MambaBack: Bridging Local Features and Global Contexts in Whole Slide Image Analysis

    Apr 17, 2026Sicheng Chen, Chad Wong, Tianyi Zhang +3Efficient Neural Network InferenceMultiple Instance Learning

  15. PC-MIL: Decoupling Feature Resolution from Supervision Scale in Whole-Slide Learning

    Apr 13, 2026Syed Fahim Ahmed, Gnanesh Rasineni, Florian Koehler +7Whole-Slide Image AnalysisHistopathology Image Classification

  16. AC-MIL: Weakly Supervised Atrial LGE-MRI Quality Assessment via Adversarial Concept Disentanglement

    Apr 11, 2026K M Arefeen Sultan, Kaysen Hansen, Benjamin Orkild +7Medical Image Quality AssessmentMedical Image Analysis

  17. Region-Graph Optimal Transport Routing for Mixture-of-Experts Whole-Slide Image Classification

    Apr 8, 2026Xin Tian, Jiuliu Lu, Ephraim Tsalik +3Histopathology Image ClassificationWhole-Slide Image Analysis

  18. Frailty Estimation in Elderly Oncology Patients Using Multimodal Wearable Data and Multi-Instance Learning

    Apr 8, 2026Ioannis Kyprakis, Vasileios Skaramagkas, Georgia Karanasiou +10Clinical PredictionClinical Risk Prediction

  19. Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning

    Mar 23, 2026Daniel Shao, Joel Runevic, Richard J. Chen +4Multiple Instance LearningHistopathology Image Classification

  20. MIHT: A Hoeffding Tree for Time Series Classification using Multiple Instance Learning

    Mar 23, 2026Aurora Esteban, Amelia Zafra, Sebastián VenturaInterpretable Time-Series ClassificationTime Series Classification

  21. Jigsaw Regularization in Whole-Slide Image Classification

    Mar 20, 2026So Won Jeong, Veronika RočkováHistopathology Image ClassificationWhole-Slide Image Analysis

  22. SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning

    Mar 20, 2026Nikola Jovišić, Milica Škipina, Vanja ŠvendaGenerative ModelingSynthetic Data Augmentation

  23. ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis

    Mar 20, 2026Lubin Gan, Jing Zhang, Heng Zhang +4Histopathology Image ClassificationMedical Image Localization

  24. Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysis

    Mar 16, 2026Umar Marikkar, Muhammad Awais, Sara AtitoWhole-Slide Image AnalysisComputational Pathology

  25. Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning

    Mar 14, 2026Sungrae Hong, Jiwon Jeong, Jisu Shin +4Multiple Instance LearningCost-Sensitive Learning

  26. Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading

    Mar 10, 2026Marie Arrivat, Rémy Peyret, Elsa Angelini +1Prostate Cancer GradingHistopathology Image Classification

  27. MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification

    Mar 10, 2026Nikola Jovišić, Milica Škipina, Nicola Dall'Asen +1Mammography Image ClassificationMedical Image Classification