Cited by 740Machine Learning and AlgorithmsMachine Learning and Data ClassificationDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 221 of the 223 references it cites were found in a registry or an index.

Multiple instance learning: A survey of problem characteristics and applications

Open access

Carbonneau, Marc-André, Cheplygina, Veronika, Granger, Eric, Gagnon, Ghyslain·2018·Pattern Recognition

DOI 10.1016/j.patcog.2017.10.009

Open this paper in CoChat — free account Open PDF

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Integrity signals

Registry

Crossref · 10.1016/j.patcog.2017.10.009

Cites

221 of 221 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · cited 2×
“There are external methods like SMOTE [193] and RUSBoost [194] that necessitate accurate labels to perform over or under sampling.”
Method
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · cited 1×
“The method is essentially the same as gradient boosting [143] except that the loss function is based on bag classification error.”
Method
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
The WEKA data mining software: an update
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1656274.1656278 · Cited by 17,750
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“Recently, methods for representation learning [160] have gained in popularity because they usually yield a high level of accuracy.”
Method
Statistical Comparisons of Classifiers over Multiple Data Sets
Demšar, J. (2006) · doi:10.5555/1248547.1248548 · Cited by 12,051
Cross validatory choice and assessment of statistical predictions
Stone, M. (1974) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1974.tb00994.x · Cited by 10,881 · cited 1×
“The experiments were conducted using a nested cross-fold validation protocol [149].”
Method
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916 · cited 1×
“In BoW models for computer vision, this can be achieved by dividing the images [102, 103] or videos [80] into different spatial and/or temporal zones.”
The Earth Mover's Distance as a Metric for Image Retrieval
Rubner, Y., Tomasi, C., & Guibas, L. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026543900054 · Cited by 5,547

Show all 223 references

Research works printed but not linked: 1

Babenko, 2011, Robust object tracking with online multiple instance learning, IEEE Trans. Pattern Anal. Mach. Intell., 33, 1619, 10.1109/TPAMI.2010.226 · DOI · Paper page

Sorted by citations

Items 601–700 of 734

Investigating intra-tumor heterogeneity in non-small cell lung cancer using multiplexed immunohistochemistry and deep learning
Noureddine, K., Gallagher, P., Thomas, G., Lam, S. F., MacAulay, G. D., McGuire, A., English, J. C., Guillaud, M. D., & MacAulay, C. E. (2022) · SPIE Medical Imaging: Digital and Computational Pathology · doi:10.1117/12.2624042
Evidence Transfer: Learning Improved Representations According to External Heterogeneous Task Outcomes
Davvetas, A., Klampanos, I., Skiadopoulos, S., & Karkaletsis, V. (2022) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3502732
“Inexact supervision includes cases where labelled bags of instances are available instead of individually learned instances, similar to Multiple Instance Learning [4].”
Background
Event stream classification with limited labeled data for e-commerce monitoring
Zimin, A., Mishchenko, I., & Steinert, R. (2021) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs54544.2021.00089
Pornographic Image Recognition Based on Multi-Instance Deep LearningPreprint
Daxiang, L. I., Ji, Z., & Liu, Y. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4049626
ENSEMBLE-BASED INSTANCE RELEVANCE ESTIMATION IN MULTIPLE-INSTANCE LEARNINGPreprint
Waqas, M., & Qureshi, R. (2021) · doi:10.36227/techrxiv.14945712
Transfer Machine Learning Algorithms
Singh, N., & Roy, N. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-822548-6.00125-4
Solar: Science of Entity Loss Attribution
Mourya, A., Sircar, P., Majumder, A., & Gupta, D. K. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539087
Multi-instance learning by maximizing the area under receiver operating characteristic curve
Sakarya, I. E., & Kundakcioglu, O. E. (2022) · Journal of Global Optimization · doi:10.1007/s10898-022-01219-y
Lung nodules identification in CT scans using multiple instance learning.
Safta, W. (2021) · doi:10.18297/etd/3793
Local feature selection for multiple instance learning with applications.
Shahrjooihaghighi, A. (2021) · ThinkIR: The University of Louisville's Institutional Repository (University of Louisville) · doi:10.18297/etd/3761
Learning from limited labelled data: contributions to weak, few-shot, and unsupervised learning
Rodríguez, J. J. S. (2022) · RiuNet (Universitat Politècnica de València) · doi:10.4995/thesis/10251/190633
Effective and Interpretable Information Aggregation with Capacity Networks
Zopf, M. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892234
“Many works on multiple instance classification [2], [5] and regression [6], [23] make strong task-specific assumption [7].”
Background
Deep Learning using Susceptibility-Weighted MR Sequence to Detect Microbleeds and Classify Cerebral Small Vessel DiseasePreprint
Wu, R., Liu, H., Li, H., Chen, L., Wei, L., Huang, X., Liu, X., Men, X., Li, X., Han, L., et al. (2023) · medRxiv · doi:10.1101/2023.03.30.23287989
“Next, a multi-instance learning (MIL) network was applied to classify CSVD sequence-wise.(25) Semantic segmentation masks of CMBs generated by Mask-RCNN were then spliced with the original corresponding SWS to form a double-channel image as the model's input for classifying CSVD, inducing the”
Method
Random field losses for deep networks
Ayed, I. B. (2023) · Elsevier eBooks · doi:10.1016/b978-0-12-805320-1.00014-2
Co-teaching module for multiple instance learning-based weakly supervised object detection network
Shang, H. (2023) · International Conference on Computer Vision and Pattern Analysis (ICCPA) · doi:10.1117/12.2684357
“Subsequently, the convolutional neural classification network is trained using multi-instance learning [5] to classify the proposals.”
Method
A Novel Weakly Supervised Learning Method for Industrial Surface Defect Detection
Huang, Y., Liu, B., Dong, H., Lu, B., Jiang, Y., & Liu, G. (2023) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd57115.2023.10206091
“Multiple instance learning [14] is a classical weakly supervised learning method, but it is more effective in object detection tasks.”
Machine Learning Service Recommendation Based on Accuracy Related QoS Attributes
Alghofaily, B. (2023) · doi:10.32920/24043236
Machine Learning Service Recommendation Based on Accuracy Related QoS Attributes
Alghofaily, B. (2023) · doi:10.32920/24043236.v1
Foreground-Background Joint Modeling Based on Inter-Segment Action Feature Enhancement for Weakly-Supervised Temporal Action LocalizationPreprint
Liu, P., Wang, C., Wang, C., Qin, J., & Wang, J. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4567047
DISCIPLINE TECHNIQUES AND SCHOOL COMMITMENT AS PREDICTORS OF DELINQUENCY AMONG SECONDARY SCHOOL STUDENTS IN KWARA STATE
Balogun, A. O. (2023) · International Journal of Advanced Humanities Research · doi:10.21608/ijahr.2023.230551.1023
Métodos fracamente supervisionados para classificação de ácaros na citricultura
Bollis, E. R. (2022) · doi:10.47749/t/unicamp.2022.1249064
Multi-Instance Bias Suppression for Enhanced Generalization in Breast Cancer Diagnosis : Harnessing Histopathological Big Data Insights
Shah, S. A., Zeng, X., Ahmed, A., Parvez, S., Xi, R., & Hou, M. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386103
Bag-Based Feature-Class Correlation Analysis for Multi-Instance Learning Application
Berahim, M., Samsudin, N. A., Mustapha, A., Salleh, R. M., & Nasir, M. J. M. (2024) · PaperAsia · doi:10.59953/paperasia.v40i1b.57
Learning Hybrid Negative Probability Model for Weakly-Supervised Whole Slide Image Recognition
Qiu, Y., Li, Y., Wu, J., Gan, Z., Chi, M., Wang, Y., Wang, C., & Wang, P. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448100
“Secondly, negative bags have naturally available patch-wise labels, and the appearance of normal tissues in WSIs usually manifests limited patterns [15].”
Background
Modeling multiple‐criterion diagnoses by heterogeneous‐instance logistic regression
Yang, C., Li, M., Wen, S., & Chang, S. (2024) · Statistics in Medicine · doi:10.1002/sim.10202
“Some of these MIL methods were implemented in the MATLAB toolbox “MILSurvey” 20 and a Python package.”
Neighborhood Component Feature Selection for Multiple Instance Learning Paradigm
Turri, G., & Romeo, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70341-6_14
Shape-Background Joint-Aware Multiple Instance Learning for Small Tumor SegmentationPreprint
Liu, H., Gou, S., Zhou, Y., Jiao, C., Liu, W., Shi, M., & Luo, Z. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4952323
Multiple-Instance Learning from Pairwise Comparison Bags
Zhou, S., Shu, S., Wang, H., Wei, H., Xiang, T., & Li, B. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3696460
“Differently from traditional supervised learning, multiple-instance learning (MIL) [1, 11, 15] focuses on the binary classification problem based on a dataset of bags containing multiple instances instead of individual instances.”
Influence Beyond Similarity: A Contrastive Learning Approach to Object Influence Retrieval
Liberatore, T., Groth, P., Kackovic, M., & Wijnberg, N. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-77792-9_3
Contrastive Pre-Training and Multiple Instance Learning for Predicting Tumor Microsatellite Instability
Nap, R., Aburidi, M., & Marcia, R. F. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782037
“In the context of studying WSIs, a notable instance of weakly supervised learning is Multiple Instance Learning (MIL) [10].”
DC Optimization Models for Machine Learning
Astorino, A., & Fuduli, A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00180-9
Not seeing the trees for the forest. The impact of neighbours on graph-based configurations in histopathology
Fourkioti, O., Vries, M. D., Naidoo, R., & Bakal, C. (2025) · BMC Bioinformatics · doi:10.1186/s12859-024-06007-x · Cited by 2
SiameseNet based on multiple instance learning for accurate identification of the histological grade of ICC tumors
Fu, Z., Feng, F., He, X., Li, T., Li, X., Ziluo, J., Huang, Z., & Ye, J. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1450379
“MIL represents a type of weakly-supervised classi ﬁ cation that depends solely on patient-level labels, where each slice is treated as an individual instance, and a single case or patient data comprising multiple slices is treated as a “ bag ” (18, 19).”
Classification of endoscopic capsule pathologies using Multiple Instance Learning methods
Moreira, V., Machado, E., Barbosa, D., Salgado, M., Bráz, G., & Cunha, A. M. T. D. S. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.02.219 · Cited by 1
CPL: Curriculum Pseudo Labeling for Weakly Supervised Temporal Forgery Localization
Zhang, D., Fang, M., Lu, Z., & Xie, H. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887844
ReViT: A Hybrid Approach for BCLC Staging of Hepatocellular Carcinoma Using 3D CT with Multiple Instance Learning
Chang, S., Yu, H.-P., Hsieh, Y.-H., Wang, P., Wang, W., Su, T., Kao, J., & Lin, C. (2024) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi62660.2024.10913759
Toward Foundation Models: A Simple Approach for Building Large Event Recognition Models [LERM] Using Federated Multi-instance Knowledge Distillation
Kar, I., Mukhopadhyay, S., & Ralte, Z. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-0143-1_5
Machine Learning Problem Framing
Subramanian, V. (2025) · doi:10.1002/9781394155408.ch4
Leakage Prediction in Real-World Water Distribution Networks Using Multi-Objective Multi-Gene Genetic Programming
Hayslep, M., Keedwell, E. C., & Farmani, R. (2025) · ACM Transactions on Evolutionary Learning and Optimization · doi:10.1145/3729431
Optimizing Anti-VEGF Treatment Strategies with AI-Based Neovascular AMD Detection
Ding, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-86651-7_14
Attention-Based Multiple Instance Learning for Achilles Tendinopathy Detection in Ultrasound Imaging
Formby, B., Wang, K., & Smith, D. H. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10981252
“This strategy is based on the standard MIL assumption that a bag label is positive if any instances within the bag are positive [8].”
Weakly supervised free-space segmentation by fusing spatial priors and region features for auto-driving
Huang, D., Wang, H., Zhao, Y., Guo, F., Zhang, F., Chen, P., Yang, C., & Gui, W. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01855-w
“Early approaches [16, 17] treat this task as Multiple Instance Learning (MIL) problem with each image being regarded as a package containing at least one pixel of the known classes, which fails to consider localization information of objects.”
Resisting Bag-Based Attribute Profiling by Adding Adversarial Items to Existing Media Profiles
Liu, Z., Zhao, Z., & Larson, M. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3574977
“Common late fusion strategies include voting and pooling [45].”
Connecting instance and model sparsity in multiple instance learning
Riccardi, E., Minotto, T., Haff, I. H., & Sandve, G. K. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100679
Estimating Node Abnormalities From Imprecise Subgraph-Level Supervision
Peng, Z., Xue, Y.-Q., Wang, Y., Lin, Q.-K., & Shen, C. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3593338
A Comparative Study of a Real-Time Multi-Person Tracking System in an Urban Square Dataset
Jafarzadeh, P., Zelioli, L., Farahnakian, F., Nevalainen, P., & Heikkonen, J. (2025) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc64332.2025.11118548
“Various MIL approaches, including instance-space and embedding-space methods, have been proposed to improve robustness and accuracy in real-world scenarios [32].”
DwinTMIL: An Innovative Approach for Helicobacter Pylori Infection Classification
Jiang, S., & Lv, Z. (2025) · IEEE International Conference on Image Processing and Computer Applications (ICIPCA) · doi:10.1109/icipca65645.2025.11138896
“Most existing datasets are labeled at the patient level rather than the image level [4].”
263Advanced machine learning models for accurate and efficient anomaly detection in scanned visual data
Shetty, M. P., Praveena, S., Manivelmuralidaran, V., Shetty, S. B., Anupriya, R., & Senthilkumar, P. (2025) · De Gruyter eBooks · doi:10.1515/9783112205198-006
Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning
Hasan, M. (2025) · Mathematics and Computer Science · doi:10.11648/j.mcs.20251004.11
How Useful Is Graph Pooling for Node-Level Tasks?
Duan, Y., Liu, X., Lynden, S. J., Matono, A., & Ma, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06066-2_6
Contextual Pooling for Multiple-Instance Learning-based Non-Intrusive Load Monitoring
Tanoni, G., Principi, E., Vitulli, P., Mandolini, L., & Squartini, S. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228935
A Bag-Instance Network for Dysarthria Detection
Liu, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227452
One-shot Active Neuron Localization with in vivo Fluorescence Image Sequences
Cheng, W., Li, Z., Ren, J., Rout, R., Pan, Y., Du, C., & Ling, H. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254320
“Considering that a region’s states on individual frames determine its type (active neuron or background), and neurons typically maintain stable positions over time, we formulate this task as a new one-shot multiple instance learning (MIL) problem [12].”
Enhanced Multiple Instance Learning for Breast Cancer Detection in Mammography: Adaptive Patching, Advanced Pooling, and Deep Supervision
Sarwar, F., Garrido, N. M. D. F., Sebastião, P., & Silveira, M. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254317
“This makes MIL a weakly supervised method [6].”
MPT-MIL: Multimodal Aware Prompt Tuning for Prediction of Cancer Survival
Zhang, R., Fang, M., Liu, S., Wang, Z., Xie, X., Ma, X., Tian, J., & Dong, D. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3640398
“During the ﬁne-tuning process of re-training feature extractors, a key challenge remains in determining how to effectively utilize weak labels of WSIs, given the presence of both disease-related and unrelated normal tissues in pathological images [24].”
TEWS: Transformer-empowered weakly supervised prediction of immune score and genetic mutations in liver cancer from whole slide image
Wang, B., Chen, X., Li, Y., Wang, H., Wang, K., & Li, X. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108837 · Cited by 1
A novel streaming data-based video anomaly detection method with adaptive feature selection
Aydoğdu, Ö., & Aydoğdu, M. C. (2025) · The Visual Computer · doi:10.1007/s00371-025-04311-y
“Instead of requiring precise labels for each individual object (object level), weakly labeling operates at the bag level, leveraging information about groups of instances [57].”
Additional file 1 of Deep learning based on susceptibility-weighted MR sequence for detecting cerebral microbleeds and classifying cerebral small vessel disease
Wu, R., Liu, H., Li, H., Chen, L., Wei, L., Huang, X., Liu, X., Men, X., Li, X., Han, L., et al. (2024) · Figshare · doi:10.6084/m9.figshare.26627725
Uncertainty-aware weakly supervised temporal action localization with knowledge selection
Yan, H., Sun, B., & He, J. (2025) · Displays · doi:10.1016/j.displa.2025.103215
Spatial Annotation-Free Sound Event Localization and Detection via Spatial Instance Classification
Yasuda, M., Harada, N., Saito, S., & Ono, N. (2025) · IEEE Access · doi:10.1109/access.2025.3609479
“…collective assumption , p ( y | X ) can be expressed in terms of the instance posteriors p ( y | x i ) and non-negative weights w i as follows [15]: The parameters θ in the estimator of ˆ p ( y | X ) can be trained with the following loss function : where y c is the ground-truth label…”
General introduction
Dolz, J., Ayed, I. B., & Desrosiers, C. (2025) · Elsevier eBooks · doi:10.1016/b978-0-32-395674-1.00007-x
Weakly supervised segmentation
Dolz, J., Ayed, I. B., & Desrosiers, C. (2025) · Elsevier eBooks · doi:10.1016/b978-0-32-395674-1.00010-x
A unified view of learning from both labeled and unlabeled data
Dolz, J., Ayed, I. B., & Desrosiers, C. (2025) · Elsevier eBooks · doi:10.1016/b978-0-32-395674-1.00008-1
Improving multiple instance contrastive learning via sparse transformer for whole slide image classification
Liu, Z., Lu, M., Xia, Y., Liu, W., & Shu, M. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108714
ГЛУБОКИЙ ЛЕС ДЛЯ АНАЛИЗА ВЫЖИВАЕМОСТИ В РАМКАХ МНОГОВАРИАНТНОГО ОБУЧЕНИЯ
Konstantinov, A. V., & Utkin, L. V. (2025) · Высшая школа: научные исследования · doi:10.15622/rcai.2025.072
A Power Quality Disturbance Recognition Method Based on Generative Adversarial Network and Multi-Instance Learning
Liu, J., Yi, S., Liu, J., Wang, J. C., Huang, J., Li, Z., & Sun, J. (2025) · IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA) · doi:10.1109/ispce-asia69076.2025.11312814
“This approach requires only bag-level labels for model training, significantly reducing annotation effort [19].”
Set-Input Trees: An Interpretable Multiple Instance Learning Architecture for Robotics
Konstantinov, A., & Utkin, L. V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-11903-2_15
SG-MuRCL: Smoothed Graph-Enhanced Multi-Instance Contrastive Learning for Robust Whole-Slide Image Classification
Ziabari, S. S. M., Lin, B. Y., Husaini, Y. N. A., & Alsahag, A. M. M. (2026) · Information · doi:10.3390/info17010037 · Cited by 1
“In this setting a slide is divided into many small patches that form a bag, and supervision is provided only at the bag level [3].”
Shared control in robotic brain-computer interfaces: can we stop chasing our tail?
Thomas, A., Cho, Y., Zhao, H., & Carlson, T. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.12.488
Weakly Labeled Ovarian Cancer Pathological Image Classification Based on Self-Supervised and Multi-Relational Graph Learning
Zhang, S., Zhang, Z., Wang, B., Shi, J., & Jin, H. (2025) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin64977.2025.11279183
“Multiple instance learning (MIL) [9]–[11], as a weakly supervised learning paradigm, treats an entire WSI as a “bag” containing multiple local image patches (instances), requiring only bag-level labels for classification and prediction.”
PATHOS: Pathology attention framework for treatment response stratification in ovarian high-grade serous carcinomas following neoadjuvant chemotherapy on H&E images
Miccolis, F., Lovino, M., Lehtonen, O., Hynninen, J., Hautaniemi, S., Virtanen, A., & Ficarra, E. (2026) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2026.100545
“…there is an urgent need for accurate and interpretable methods to characterize the histopathological features associated with treatment response in HGSC. Multiple instance learning (MIL) 5,25 has emerged as a powerful tool for analyzing image data, particularly in the context of pathology.”
Imbalanced Multiclassification Challenges in Whole Slide Image: Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning With Dynamic Rebalancing
Wu, Y., Xie, X., Zhao, C., Song, P., Yin, F., Wu, G., & Yu, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3654402
“Since the introduction of MIL concepts for pathological image analysis [8], WSI data has typically been organized as bags for processing, where each bag contains multiple instances but only one bag-level label.”
Natural language-based representation and modeling of RBP bindingPreprint
Elhajjajy, S. I., & Weng, Z. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.05.704032
“In this formulation, we treat sequences as “bags” with known labels, and regions as “instances” of bags with unknown labels; our objective is to determine which of the region(s) (i.e., key instance[s]) within a bound sequence significantly contribute to its positive label [6, 7].”
Influential
Anomaly Detection Method for Tabular Data Based on a Three-Phase Learning Paradigm
Li, Y., Song, H., & Han, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7138-3_7
Research on Expert Knowledge-Guided Visual-Semantic Feature Extraction Algorithms
Yao, S., Cui, L., Wang, F., Liu, Y., & Xu, W. (2025) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/ic-nidc67200.2025.11390300
“We employ a multi-instance learning (MIL) strategy [14] to fuse classification results across a patient’s images for a more robust diagnosis.”
Learning from Two-Sample-Averaged Data
Matsuno, R., & Kitaoka, A. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00066
Intrinsic interpretability at parity: Attention-Based RL–MIL for student outcome prediction
Braakman, N. M., Ziabari, S. S. M., Alsahag, A. M. M., & Husaini, Y. N. A. (2026) · Natural Language Processing Journal · doi:10.1016/j.nlp.2026.100204
AI-Aided Triage for GSWH: Validating an Interpretable HCT-Based Mortality Model
Mansour, A. R., Fuhrman, J. D., Alvarado-Dyer, R., Badillo‐Goicoechea, E., Lo, E., Fakhri, F., Nugent, J., Desai, H., Lawrence, M., Pasternak, O., et al. (2026) · Journal of Neurotrauma · doi:10.1177/08977151261429994
ACRNet: high-resolution whole slide images classification network based on adaptive core regions
Fu, Z. L. Z. W. P. L. W. L. J., Chen, Q., Wang, M., & Huang, C. (2026) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-026-03544-w
Weakly Supervised Learning for Facial Affective Behavior Analysis: A Review
Praveen, R. G., Cardinal, P., & Granger, É. (2026) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2026.3677128 · Cited by 4
“Expression Classiﬁcation: This task can be formulated as static or dynamic FER, aiming to identify the spatial or temporal regions most indicative of expressions (see Fig.”
Weak supervised learning survey for time series data: contemporary approaches, unresolved challenges, and prospective research avenues
Gupta, P., Gupta, M., & Kumar, V. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae5875
Interpretable Similarity of Synthetic Image Utility
Gatoula, P., Dimas, G., & Iakovidis, D. K. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3679527 · Cited by 2
“Thus, following the approach described in [44], the maximum probability among the image-level predictions of a sequence, was used as the representative classiﬁcation score for that sequence.”
XMR-Net: Residual-corrected blast-hole hierarchical learning for blast fragmentation predictionPreprint
Seo, S., Chung, M., Ko, Y., & Kim, G. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6511804
Apprentissage automatique pour déduire le comportement des utilisateurs dans les réseaux autonomes 5G
Saffara, I. (2020) · theses.fr (ABES) · doi:10.70675/d8ec58afz1d24z47d3z9a07z42baef2367ca
Cancer Detection in Full Field Optical Coherence Tomography Images
Mandache, D. (2022) · theses.fr (ABES) · doi:10.70675/a8e12287zf665z4a1fz822fze7174f880867
Transfer learning of convolutional neural networks for texture synthesis and visual recognition in artistic images
Gonthier, N. (2021) · theses.fr (ABES) · doi:10.70675/9abc66b4zca61z423bz85dcz07b849b15209
Identification de vêtements dans des images : de la segmentation d'instances à la classification multi-étiquettes faiblement supervisée
Jouanneau, W. (2023) · theses.fr (ABES) · doi:10.70675/ad882444z34d7z44e0zaeeez1ba7b4d7958c
Biquality learning : from weakly supervised learning to distribution shifts
Nodet, P. (2023) · theses.fr (ABES) · doi:10.70675/41d22fb9z3d38z4a64z9a3cz4a385058629c
Exploiting Heterogeneous Labels in Deep Learning for Medical Image Analysis : Application to the Automated Diagnosis of Liver Diseases
Sarfati, E. (2025) · theses.fr (ABES) · doi:10.70675/c8de34e7z1fa6z42cbza183z1e37c1b52362
HyperMIL: Hypergraph-Based Channel Reasoning for Multiple Instance Learning on Multivariate Time Series
Gaudio, L. D., Cuculo, V., & Cucchiara, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31654-7_15
Active Learning for Budget-Constrained TCR–pMHC Wet-Lab ValidationPreprint
Kowalski, J., Mazur, K., & Piotrowska, M. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.14.718510
“Under distribution shift, diversity-aware strategies are particularly important because uncertainty scores become unreliable for out-of-distribution examples [6], [15].”
Hybrid supervised deep learning for lung adenocarcinoma diagnosis to optimize surgical strategies
Zhao, J., Zhang, J., Wang, Y., Zhong, X., & Guan, X. (2026) · npj Precision Oncology · doi:10.1038/s41698-026-01441-x
“Inrecentyears,theemergenceofweaklysupervisedlearningmethods, particularlyMultipleInstanceLearning(MIL) 12 – 14 ,hassigni ﬁ cantlyreduced annotation costs through slide-level labels, demonstrating notable advantages in whole slide image (WSI) classi ﬁ cation tasks 15 .”
Graph-based multi-instance learning: a survey
Ye, G., Zhou, X., Liu, C., & Wang, R. L. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03102-8
“Carbonneau et al. [18] starts from the perspective of non-i.i.d. instances, and introduces several representative approaches for modeling instance dependencies, but due to its early publication date, it does not cover the MIL meth-ods developed since 2019 that incorporate graph neural networks.”
SCPLoc: A weakly-supervised multi-instance learning framework for protein subcellular localization and heterogeneity profiling in single-cell immunofluorescence images
Li, Y.-L., Wang, Y.-Y., Zhu, X.-L., He, Y., Zhou, Q., & Xu, Y.-Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133825
Cheatomaly: weakly supervised video anomaly ranking for exam cheating detection using vision transformers
Mrani, E. M. A., Bouayad, A., & Fardousse, K. (2026) · Frontiers in Big Data · doi:10.3389/fdata.2026.1817120
One Class Fault Detection in Rotating Machinery Using Distributional Features from Triggered Acoustic Emission Data
Angelopoulos, N., Georgoulas, G., & Kappatos, V. A. (2026) · Electronics · doi:10.3390/electronics15102105
REMIL-IBD: Region-filtered multiple instance learning for interpretable slide-level grading of inflammatory bowel disease
Banerjee, A., Aasprong, O. G., Janssen, E., van der Giezen, M., Grimstad, T. B., & Engan, K. (2026) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2026.100674
Hybrid DenseNet-U-Net framework for automated grading of renal cell carcinoma
Jadhav, R., Mohapatra, B., Walia, B., Dash, S., Patil, K. R., Jadhav, S., & Raskar, I. R. (2026) · Digital Health · doi:10.1177/20552076261453125
“,25–28 These approaches have improved predictive performance on public and multi-center datasets, often reporting macro-F1 values above 0.90.”
Influential
Multisource Feature Aggregation Approach for Predicting Extreme Pitting Depth Distributions of In Situ Bridge Cable Wires
Zhang, H. J., Xin, Y., Yao, L., Zheng, X., & Zhang, Z. (2026) · Journal of Bridge Engineering · doi:10.1061/jbenf2.beeng-8078
TopoMIL: Topology Improves Multiple Instance Learning in Diagnostic Microscopic ImagesPreprint
Kazeminia, S., Dasdelen, M. F., Rieck, B., & Marr, C. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.10.731443
“Multiple Instance Learning (MIL) is a widely adopted machine learning paradigm well-suited for this type of weakly labeled data 5,6 .”

Authors: Carbonneau, M.-A., Cheplygina, V., Granger, E., & Gagnon, G.
Affiliations: École de Technologie Supérieure (CA)
Erasmus MC (NL)
Corresponding author: Carbonneau, Marc-André
ORCID: Carbonneau, Marc-André
Cheplygina, Veronika
Gagnon, Ghyslain
Venue: Pattern Recognition
Publisher: Elsevier BV
Published: 2018-05
Volume: 77
Pages: 329-353
ISSN: 0031-3203 (ISSN-L)
DOI: 10.1016/j.patcog.2017.10.009
OpenAlex: W2560886373
Cited by: 740
References: 223
Citations by year: 2026: 75 · 2025: 118 · 2024: 91 · 2023: 124 · 2022: 98 · 2021: 92 · 2020: 84 · 2019: 41 · 2018: 14
FWCI: 22.10
Type: journal article
Language: en
Open access: green
arxiv.org
Licence: www.elsevier.com/tdm/userlicense/1.0/ (tdm)
Locations: Pattern Recognition (publishedVersion)
arXiv (Cornell University) (submittedVersion)
TU/e Research Portal (submittedVersion)
EUR Research Repository (Erasmus University Rotterdam) (submittedVersion)
Espace ÉTS (ETS) (submittedVersion)
TU/e Research Portal (submittedVersion, other-oa)
RePub (Erasmus University Rotterdam) (submittedVersion, other-oa)
arXiv (Cornell University)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords: multiple instance learning, weakly supervised learning, problem characteristics, data distribution, label ambiguity, computer vision, document classification

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Multiple instance learning: A survey of problem characteristics and applications

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks