mlsanityData to 7 Oct 2026

Multiple Instance Learning: A Survey of Problem Characteristics and Applications

arXiv 1612.03365 ↗First posted 11 Dec 2016cs.CV cs.AI cs.IRcited by 163

Not on the map. Why?

Abstract (arXiv)

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research.

Key facts. Cited by 163 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 33; 2023: 30; 2024: 27; 2025: 29; 2026: 14.

163 papers.

Sort:

By area:

  1. 2023Federated Learning for Medical Image Analysis: A Surveycited by 77
  2. 2022Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potentialcited by 54
  3. 2021Learning to Select Cuts for Efficient Mixed-Integer Programmingcited by 48
  4. 2022Transformers in Medical Image Analysis: A Reviewcited by 41
  5. 2023On Sparse Modern Hopfield Modelcited by 41
  6. 2023A Deep Neural Architecture for Harmonizing 3-D Input Data Analysis and Decision Making in Medical Imagingcited by 39
  7. 2021Deep Learning-based Action Detection in Untrimmed Videos: A Surveycited by 32
  8. 2021Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imagingcited by 31
  9. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  10. 2021Inductive Relation Prediction by BERTcited by 27
  11. 2022AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Imagescited by 24
  12. 2023Weakly Supervised Anomaly Detection: A Surveycited by 22
38 more
  1. 2021Weakly Supervised Action Selection Learning in Videocited by 21
  2. 2025Robust Hallucination Detection in LLMs via Adaptive Token Selectioncited by 19
  3. 2023Label-Efficient Learning in Agriculture: A Comprehensive Reviewcited by 16
  4. 2024Nonparametric Modern Hopfield Modelscited by 16
  5. 2024xMIL: Insightful Explanations for Multiple Instance Learning in Histopathologycited by 15
  6. 2025A Survey of Pathology Foundation Model: Progress and Future Directionscited by 14
  7. 2022Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learningcited by 13
  8. 2022Movies2Scenes: Using Movie Metadata to Learn Scene Representationcited by 11
  9. 2023Weakly Supervised AUC Optimization: A Unified Partial AUC Approachcited by 11
  10. 2023Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Testscited by 11
  11. 2022Model Agnostic Interpretability for Multiple Instance Learningcited by 10
  12. 2022DSCA: A Dual-Stream Network with Cross-Attention on Whole-Slide Image Pyramids for Cancer Prognosiscited by 10
  13. 2023Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directionscited by 10
  14. 2024Sm: enhanced localization in Multiple Instance Learning for medical imaging classificationcited by 10
  15. 2021MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal datacited by 9
  16. 2021WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Imagescited by 9
  17. 2023Disambiguated Attention Embedding for Multi-Instance Partial-Label Learningcited by 9
  18. 2023A Unified Approach to Count-Based Weakly-Supervised Learningcited by 9
  19. 2022Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actionscited by 8
  20. 2022RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learningcited by 8
  21. 2022Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervisioncited by 8
  22. 2024CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attentioncited by 8
  23. 2021Nested Multiple Instance Learning with Attention Mechanismscited by 7
  24. 2022Using Multiple Instance Learning to Build Multimodal Representationscited by 7
  25. 2023Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learningcited by 7
  26. 2024PATHS: A Hierarchical Transformer for Efficient Whole Slide Image Analysiscited by 7
  27. 2021Seeking an Optimal Approach for Computer-Aided Pulmonary Embolism Detectioncited by 6
  28. 2021Multi-Attention Multiple Instance Learningcited by 6
  29. 2022Open challenges for Machine Learning based Early Decision-Making researchcited by 6
  30. 2022Multiple Instance Neuroimage Transformercited by 6
  31. 2022Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labelscited by 6
  32. 2024Action Selection Learning for Multi-label Multi-view Action Recognitioncited by 6
  33. 2025Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Studycited by 6
  34. 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoringcited by 6
  35. 2021Learning with Group Noisecited by 5
  36. 2021Machine Learning for Fraud Detection in E-Commerce: A Research Agendacited by 5
  37. 2022Psychophysiological Arousal in Young Children Who Stutter: An Interpretable AI Approachcited by 5
  38. 2023ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classificationcited by 5

50 most cited of 163 All 163 (JSON)