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 501–600 of 734

Fall event detection with global and temporal local information in real-world videos
Pang, W., He, Q., Chen, Y., & Li, Y. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12018-8 · Cited by 2
Dealing With Multipositive Unlabeled Learning Combining Metric Learning and Deep Clustering
Racanati, A., Esposito, R., & Ienco, D. (2022) · IEEE Access · doi:10.1109/access.2022.3174590 · Cited by 2
“Among them, it is worth mentioning active learning [3], semi-supervised learning [4], multi-instance learning [5], learning with label noise [6] and positive unlabelled learning (PUL) [7].”
Background
Route to Time and Time to Route: Travel Time Estimation from Sparse Trajectories
Zhang, Z., Wang, H., Fan, Z., Chen, J., Song, X., & Shibasaki, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26422-1_30 · Cited by 2
Graph Representation for Weakly-Supervised Spatio-Temporal Action Detection
Singh, D. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10192033 · Cited by 2
“The weakly supervised approaches mostly belong to the multiple instance learning (MIL) [2] and apply the supervised model on frame/pixels by formulating the loss function us-ing clip level annotations [20], [38], [39], [42], [45].”
Method
Automatic Labeling for Gene-Disease Associations through Distant Supervision
Teng, F., Bai, M., & Li, T. (2019) · International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · doi:10.1109/iske47853.2019.9170268 · Cited by 2
Log Data Preparation for Predicting Critical Errors Occurrences
Lopez, M., Beurton‐Aimar, M., Diallo, G., & Maabout, S. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-72651-5_22 · Cited by 2
Information-Geometric Set Embeddings (IGSE): From Sets to Probability DistributionsPreprint
Sun, K., & Nielsen, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12463 · Cited by 2
Weakly Supervised Learning Meets Ride-Sharing User Experience EnhancementPreprint
Guo, L.-Z., Kuang, F., Liu, Z.-X., Li, Y., Ma, N., & Qie, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.09027 · Cited by 2
“Typically, three types of weakly supervised data exist: incomplete supervised data (Oliver et al. 2018), i.e., only a small subset of training data is given with labels whereas the other data remains unlabeled; inaccurate supervised data (Fr´enay and Verleysen 2014), i.e., the given labels have not…”
Background
Attentive Weakly Supervised land cover mapping for object-based satellite image time series data with spatial interpretationPreprint
Ienco, D., Gbodjo, Y. J. E., Interdonato, R., & Gaetano, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.14672 · Cited by 2
“Multiple Instance Learning Multiple Instance learning [21] (MIL) is a supervised learning paradigm in which a classification model is learnt to supply prediction for a group of instances.”
Background
Kernel Self-Attention in Deep Multiple Instance LearningPreprint
Rymarczyk, D., Borowa, A., Tabor, J., & Zieliński, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.12991 · Cited by 2
Weakly Supervised Learning for Facial Behavior Analysis: A ReviewPreprint
Praveen, R. G., Cardinal, P., & Granger, É. (2024) · doi:10.36227/techrxiv.173091765.50249538/v1 · Cited by 2
Revisiting data complexity metrics based on morphology for overlap and imbalance: snapshot, new overlap number of balls metrics and singular problems prospect
Pascual-Triana, J. D., Charte, D., Arroyo, M. A., Fernández, A., & Herrera, F. (2021) · Knowledge and Information Systems · doi:10.1007/s10115-021-01577-1 · Cited by 22
Learning with Group Noise
Wang, Q., Yao, J., Gong, C., Liu, T., Gong, M., Yang, H., & Han, B. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17222 · Cited by 1
Discovering NDM-1 inhibitors using molecular substructure embeddings representations
Παπαστεργίου, Θ., Azé, J., Bringay, S., Louet, M., Poncelet, P., Rosales‐Hurtado, M., Vo‐Hoang, Y., Licznar‐Fajardo, P., Docquier, J., & Gavara, L. (2023) · Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics · doi:10.1515/jib-2022-0050 · Cited by 1
“Multiple Instance Learning has been successfully applied in different areas comprising classiﬁcation of medical images, frailty prediction by monitoring physiological signals [30], classiﬁcation of natural images [31, 32] and drug discovery [33].”
Method
GBMILs: Gradient Boosting Models for Multiple Instance Learning
Konstantinov, A. V., Utkin, L. V., Muliukha, V., & Zaborovsky, V. S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43111-1_21 · Cited by 1
Weakly Supervised Lesion Localization of Nascent Geographic Atrophy in Age-Related Macular Degeneration
Yao, H., Pely, A., Wu, Z., Gao, S. S., Guymer, R. H., Chen, H., Hejrati, M., & Zhang, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43907-0_46 · Cited by 1
Identifying Impurities in Liquids of Pharmaceutical Vials
Rosati, G., Marchesini, K., Lumetti, L., Sartori, F., Balboni, B., Begarani, F., Vescovi, L., Bolelli, F., & Grana, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78447-7_18 · Cited by 1
“…task of recognizing defective vials, we decided to explore two different paths; the former is based on the use of ResNet [16] in a slightly different way than the standard one, in order to deal with the entire sequence of images, the latter is a Multi-Instance Learning (MIL) [5] based technique.”
Multi-instance Curriculum Learning for Histopathology Image Classifications with Hard Negative Mining and Positive Augmentation
Mi, Z., Liu, X., Zhang, J., Shi, G., Li, Y., & Wu, Y. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822566 · Cited by 1
Controlling false positives in multiple instance learning: The “c-rule” approach
Delgado, R. (2025) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2025.109367 · Cited by 1
Ray-Aided Quadruple Affiliation Network for Calculating Tumor-Stroma Ratios in Breast Cancers
Yang, K., Chen, L., Zheng, X., Li, X., Lan, J., Wu, Y., Tsang, J. Y., & Tse, G. M.-K. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3561679 · Cited by 1
“[18] and semantic segmentation [19], [20] have been proposed to automatically identify di ﬀ erent morphological tissue types on H&E images.”
Multi-Scale Double-Layer Multiple Instance Learning Algorithm for Whole Slide Image Classification of Primary Gastric Lymphoma
Quan, J., Ye, J., Zhang, X., Hu, Z., Mao, Y., Liu, Y., Tong, T., & Chen, G. (2024) · International Conference on Bioinformatics and Computational Biology (ICBCB) · doi:10.1109/icbcb61507.2024.11012001 · Cited by 1
“In practical terms, this means that we can classify an entire pathological image even without exact annotations for each cell or tissue segment[15][16][17].”
SS-MIL: Attention-Based Selective Correlated Multiple Instance Learning for Whole Slide Image Classification
Makadiya, S., Reddy, K. P. K., & Gubbi, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91721-9_15 · Cited by 1
Tackling Tumor Heterogeneity Issue: Transformer-Based Multiple Instance Enhancement Learning for Predicting EGFR Mutation via CT Images
Fang, Y., Wang, M., Song, Q., Cao, C., Gao, Z., Song, B., Min, X., & Li, A. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3578995 · Cited by 1
“This limitation primarily stems from the common practice in MIL of learning instance features without explicit supervision [11], [12].”
OKEN: A Supervised Evolutionary Optimizable Dimensionality Reduction Framework for Whole Slide Image Classification
Oskouei, S., Pedersen, A., Valla, M., Dale, V. G., Wahl, S. G. F., Haugum, M. D., Langø, T., Ramnefjell, M., Akslen, L. A., Kiss, G. H., et al. (2025) · Bioengineering · doi:10.3390/bioengineering12070733 · Cited by 1
“To counteract this challenge, Multiple-Instance Learning (MIL) was proposed, in which each WSI is viewed as a “bag” of patches and the model is trained to perform bag-wise classification [28,29].”
Learning to Stop: Reinforcement Learning for Efficient Patient-Level Echocardiographic Classification
Kim, W.-J. C., OLIVEIRA, J. C., Beqiri, A., Thorley, A., Strom, J. B., O’Driscoll, J. M., Sharma, R., Slivnick, J. A., Lang, R. M., Gómez, A., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06329-8_22 · Cited by 1
Weakly Supervised Vulnerability Localization via Multiple Instance Learning
Gu, W., Chen, Y., Wang, Y., Zhang, H., Gao, C., & Lyu, M. R.-T. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3768572 · Cited by 2
“Secondly, traditional MIL approaches assume independence among instances within the same bag, implying no interaction across different instances [5].”
Punctual or Continuous? Analyzing Depression Traces in Language and Paralanguage with Multiple Instance Learning
Alsarrani, R., Esposito, A. A., & Vinciarelli, A. (2025) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3716553.3750809 · Cited by 1
Multiple Instance Learning Using Reduced Deep Learning Model For Glioma Subtype Classification
Shirae, S., Debsarkar, S. S., Kawanaka, H., Aronow, B. J., & Prasath, V. B. S. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.365 · Cited by 1
A variational Bayesian approach for multimodal multi-instance classification
Hu, Y., Cheng, Y., Xia, Y., & Wang, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112742 · Cited by 1
H&E to Oncotype DX: Predicting recurrence risk in HR+/HER2- breast cancer
Koyun, O. C., Guo, Y., Su, Z., Lü, H., Rezapour, M., Wesolowski, R., Tozbikian, G. H., Niazi, M. K. K., & Gürcan, M. N. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130469 · Cited by 1
Weakly supervised regression enables interpretable tumor detection in whole-slide histopathology without negative cases
D’Amato, M., van der Laak, J. A. W. M., & Ciompi, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-27158-8 · Cited by 1
Facilitate Robust Early Screening of Cerebral Palsy via General Movements Assessment With Multi-Modality Co-Learning
Yin, W., Huang, C., Chen, L., Huang, X., Wang, Z., Bian, Y., Zhou, Y., Wan, Y., Han, T., & Yi, M. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3641894 · Cited by 1
“Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances [31].”
Object knowledge-aware multiple instance learning for small tumor segmentation
Liu, H., Gou, S., Zhou, Y., Jiao, C., Liu, W., Shi, M., & Luo, Z. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109400 · Cited by 1
Two-stage multiple instance learning networks with attention-based hybrid aggregation for speech emotion recognition
Zhang, S., Chen, C., Wang, D., Tao, X., & Zhao, X. (2026) · Computer Speech & Language · doi:10.1016/j.csl.2026.101946 · Cited by 1
Multiple instance learning approach for automated gallbladder cancer detection using ultrasound imaging: multi-center validation of a deep learning model
Gupta, P. K., Bose, K., Mudgil, P., Dutta, N., Gulati, A., Prakash, G., Yadav, T. D., Kaman, L., Irrinki, S., Singh, H., et al. (2026) · The Lancet Regional Health - Southeast Asia · doi:10.1016/j.lansea.2026.100737 · Cited by 1
Dual Attention Multi-Instance Learning for Identifying Autism Spectrum Disorder Using Resting-State fMRI
Abbas, S. Q., Chi, L., Xia, F., Amin, N., & Chen, Y. P. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3669876 · Cited by 1
PTCMIL: multiple instance learning via prompt token clustering for whole slide image analysis
Zhao, B., Kim, S., Chen, H., Zhou, C., Gao, Z., Wang, G., & Li, X. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104013 · Cited by 4
Computer-aided discovery of CDK16 inhibitors: a docking-augmented machine learning regression modelling approach
Alfararjeh, T., Dauod, S., Hatmal, M. M., Adel, A., & Taha, M. O. (2026) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-026-00802-9 · Cited by 1
Revisiting weakly supervised tabular anomaly detection from a cell-level perspective
Wang, J., Peng, Z., Jia, X., Lin, Q., Ma, L., & Shi, B. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109202 · Cited by 1
Artificial Intelligence-Assisted Risk Stratification in Stage II Colorectal Cancer: Multi-Institutional Validation of Semantically Enhanced Deep Learning
Magisson, F., He, Z., Millward, J., Harris, A., Chen, Z., Mielke, L. A., Tran, K., Ward, R. L., Hawkins, N. J., Sieber, O. M., et al. (2026) · Gastroenterology · doi:10.1053/j.gastro.2026.07.009 · Cited by 1
XChondNet: Explainable Chondrogenic Tumor Diagnosis by Spatial-Context-Aware Synergistic Deep Feature Fusion
Xiao, S., Xie, Y., Lan, G., Liu, A., & Yang, J. (2026) · Sensors · doi:10.3390/s26175518 · Cited by 1
“Carbonneau et al. [31] provided a comprehensive survey of MIL problem settings and applications.”
A Target Detection-Based Milestone Event Time Identification Method
Zonglei, L., & Ji, T. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-04946-1_21 · Cited by 1
Deep Learning for Channel-Agnostic Brain Decoding across Multiple Subjects
Date, H., Kawasaki, K., Hasegawa, I., & Okatani, T. (2020) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci48061.2020.9061615 · Cited by 1
“Multi-instance learning [14], [15] considers each input as a set (bag) which contains a variable number of instances; thus, naturally fits this situation.”
BackgroundMethod
A Critical Evaluation of Machine Learning and Deep Learning Techniques for COVID-19 Prediction
Khero, K., & Usman, M. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-82199-9_34 · Cited by 1
Benchmarking Multi-instance Learning for Multivariate Time Series Analysis
Babayev, R., & Wiese, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-93663-1_9 · Cited by 1
Balancing Bias and Variance for Active Weakly Supervised Learning
Sapkota, H., & Yu, Q. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539264 · Cited by 1
“First, solely focusing on the most positive instance is sensitive to outliers, which are negative instances that look very different from other negative ones [3].”
Background
Deep Learning for Prognosis Using Task-fMRI
Shi, G., Smucny, J., & Davidson, I. A. K. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539362 · Cited by 1
“Unlike classic multi-view learning [33], our data doesn’t have a fixed set of features but a varying sized bag of instances to represent a view; Unlike with classic multi-instance learning [5], our goal is not to make instance-level prediction but to make bag-level predictions.”
Background
Multiple Instance Learning Based on Mol2vec Molecular Substructure Embeddings for Discovery of NDM-1 Inhibitors
Παπαστεργίου, Θ., Azé, J., Bringay, S., Louet, M., Pascal Poncelet, B., & Gavara, L. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-17024-9_6 · Cited by 1
EGSA: Enhanced and Global Semantic Activation for Weakly Supervised Object Localization
Liu, Y., Wang, L., Xu, X., & Luo, X. (2022) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc55942.2022.10004147 · Cited by 1
“Aiming at the different characteristics of the two tasks, WSOD usually adopts multi-instance learning method (MIL) [24], while models related to WSOL often optimize the category activation map (CAM).”
Method
Lung Nodules Identification in CT Scans Using Multiple Instance Learning*
Safta, W., & Frigui, H. (2022) · International Conference on Machine Learning and Applications · doi:10.1109/icmla55696.2022.00089 · Cited by 1
“Instead MI-SVM identified other instances that have larger volumes that included parenchymal structures.”
BackgroundMethodInfluential
Concentration or distraction? A synergetic-based attention weights optimization method
Wang, Z., Li, H., Ma, L., & Jiang, F. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01133-0 · Cited by 1
“…d r a ti c p r og r a mm i ng [ 55 ] P a t h e n c od i ng [ 54 ] M I n D [ 56 ] M I LE S [ 57 ] C it a ti on - k NN R e s u lt s b e l o w qu a d r a ti c p r og r a mm i ng a r e fr o m e it h e r [ 33 ] o r [ 54 ] w it h h i gh e r AU C B e s t r e s u lt s a r e m a r k e d i n bo l d 123 Fig.”
Background
Domestic Sound Classification with Deep Learning
Zhang, Z., Shen, Y., Valdés, J. J., Huq, S., Wallace, B., Green, J. R., Xi, P., & Goubran, R. A. (2023) · IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas58821.2023.10254050 · Cited by 1
“the dataset is relatively small [9], [12]–[14].”
Feature Enhancement and Foreground-Background Separation for Weakly Supervised Temporal Action Localization
Liu, P., Wang, C., Qin, J., & Lin, G. (2023) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3595916.3626423 · Cited by 1
“There are two main strategies for this purpose: the Multiple-Instance Learning (MIL) framework [1] and the attention mechanism [17].”
Method
Cervical Cytology Classification with Coarse Labels Based on Two-Stage Weakly Supervised Contrastive Learning Framework
Chai, S., Xin, J., Wu, J., Yu, H., Liang, Z., Ma, Y., & Zheng, N. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385369 · Cited by 1
“It has only coarse bag labels, and bag predictions are obtained by processing instances directly [13].”
Background
Boosting Tiny Object Detection in Complex Backgrounds Through Deep Multi-Instance Learning
Kar, I., & Mukhopadhyay, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-3245-6_20 · Cited by 1
Inexact Graph Representation Learning
Duan, Y., Liu, X., Jatowt, A., Yu, H.-T., Lynden, S. J., & Matono, A. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10649995 · Cited by 1
A comparative study of linear type multiple instance learning techniques for detecting COVID-19 by chest X-ray images
Avolio, M., Fuduli, A., Vocaturo, E., & Zumpano, E. (2024) · Progress in Artificial Intelligence · doi:10.1007/s13748-024-00332-1 · Cited by 1
Addressing Hearing Impairments through Machine Learning: A Review of Sound Detection and Assistive Technologies
Barnawi, N., & Alnuem, M. A. (2025) · Open Journal of Applied Sciences · doi:10.4236/ojapps.2025.158160 · Cited by 1
MI-CES: An explainable weak labelling approach to example selection for Motor Imagery BCI classification *
Thomas, A., Cho, Y., Zhao, H., & Carlson, T. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11253265 · Cited by 1
“2) aims to learn a concept from the differences between or areas of high data concentration in bags of data [22].”
Automatic Detection of Dysplastic Nevi: A Multiple Instance Learning Solution.
Vocaturo, E., & Zumpano, E. (2020) · Archive of Doctoral Theses and Digital Collections (University of Calabria) · Cited by 1
IsoDA: Isoform–Disease Association Prediction by Multiomics Data Fusion
Huang, Q., Wang, J., Zhang, X., Guo, M., & Yu, G. (2021) · Journal of Computational Biology · doi:10.1089/cmb.2020.0626 · Cited by 1
“To overcome this difﬁculty, some researchers have adapted multiple-instance learning (MIL) (Maron and Lozano-Pe´rez, 1998; Carbonneau et al., 2018) for isoform function prediction.”
Multiple Instance Learning for Unilateral Data
Tang, X., Luo, T., Luan, T., & Hou, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-75762-5_47 · Cited by 1
Multiple Instance Learning with Differential Evolutionary Pooling
Bhattacharjee, K., Tiwari, A., Pant, M., Ahn, C. W., & Oh, S. (2021) · Electronics · doi:10.3390/electronics10121403 · Cited by 1
“For a deeper understanding of MIL, interested readers may refer to [18,19].”
Background
Addressing Non-Representative Surveys using Multiple Instance Learning
Katz, Y., & Vainas, O. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467109 · Cited by 1
“In bag level approaches, all the instances corresponding to the bag are mapped into a single embedding in a process called pooling [23].”
Method
Few-Shot Visual Relationship Co-Localization
Teotia, R., Mishra, V., Maheshwari, M., & Mishra, A. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01603 · Cited by 1
“Meta Learning for Few-Shot Learning: Few-shot learning methods [1, 4, 8, 33] are being studied and explored significantly for both computer vision [7, 20] and natural language processing [3, 9, 22, 25, 33, 35].”
Background
Improvising Weakly Supervised Object Detection WSOD using Deep Learning Technique
Wadmare, J. G., & Patil, S. (2020) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.b3796.029320 · Cited by 1
Mining the Semantic Web with Machine Learning: Main Issues that Need to Be Known
d’Amato, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-95481-9_4 · Cited by 2
META$^\mathbf{2}$: Memory-efficient taxonomic classification and abundance estimation for metagenomics with deep learningPreprint
Georgiou, A., Fortuin, V., Mustafa, H., & Rätsch, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.13146 · Cited by 1
“It might thus be possible to exploit the co-occurrence of organisms to gain better accuracy [10].”
Background
Multi-Class Multiple Instance Learning for Predicting Precursors to Aviation Safety EventsPreprint
Bleu-Laine, M.-H., Puranik, T. G., Mavris, D. N., & Matthews, B. L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.06244 · Cited by 1
“The multiple-instance learning framework is used when labels are only available in sets called bags [33], and each bag contains many instances.”
BackgroundMethod
Training image classifiers using Semi-Weak Label DataPreprint
Zhang, A., Shah, A., & Raj, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.10608 · Cited by 1
“[6] provides an extensive summary on multiple instance learning – learning from presence/absence labels.”
mil-benchmarks: Standardized Evaluation of Deep Multiple-Instance Learning TechniquesPreprint
Grahn, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.01443 · Cited by 2
“For instance, the model learns the standard assumption for MNIST when the class of interest is [2 , 3 , 4 , 6 , 7 , 8 , 9] but not for [0 , 1 , 5] .”
Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent RepresentationsPreprint
Galovic, M., Bošanský, B., & Lisý, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.11987 · Cited by 1
“Formally, this is known as Multiple Instance Learning (MIL) [2].”
Background
ENSEMBLE-BASED INSTANCE RELEVANCE ESTIMATION IN MULTIPLE-INSTANCE LEARNINGPreprint
Waqas, M., & Qureshi, R. (2021) · doi:10.36227/techrxiv.14945712.v1 · Cited by 1
DEEMD: Drug Efficacy Estimation against SARS-CoV-2 based on cell Morphology with Deep multiple instance learningPreprint
Saberian, M., Moriarty, K., Olmstead, A. D., Hallgrimson, C., Jean, F., Nabi, I. R., Libbrecht, M. W., & Hamarneh, G. (2022) · doi:10.36227/techrxiv.19326665 · Cited by 2
Multiple Instance One-Hit Logistic Regression for Binary Classification and its Application to Bladder Cancer DetectionPreprint
Demidenko, E., Seigne, J. D., & Sokolov, I. Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4814229 · Cited by 1
Instance-Level Loss based Multiple-Instance Learning for Acoustic Scene ClassificationPreprint
Choi, W.-G., Chang, J., Yang, J., & Moon, H.-G. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/jvhpb
Multi Instance Learning For Unbalanced DataPreprint
Kozdoba, M., Moroshko, E., Shani, L., Takagi, T., Katoh, T., Mannor, S., & Crammer, K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.07010
“We refer to [2] and to [5] for a survey of recent results and applications.”
BackgroundResult
Clustering of multiple instance data.
Karem, A. (2019) · doi:10.18297/etd/3161
Prepoznavanje šarenice s pomočjo nevronskih mrež
Polanc, U., & Batagelj, B. (2020) · Računalniška obdelava slik in njena uporaba v Sloveniji (ROSUS) · doi:10.18690/978-961-286-337-1.8
Evalvacija konvolucijskih nevronskih mrež na Raspberry Pi z USB pospeševalnikom Google Coral
Čermelj, V., Peer, P., & Emeršič, Ž. (2020) · Računalniška obdelava slik in njena uporaba v Sloveniji (ROSUS) · doi:10.18690/978-961-286-337-1.10
Pupillary Distance Measurement with Fully Convolutional Neural Network
Gamulin, N., & Meden, B. (2020) · Računalniška obdelava slik in njena uporaba v Sloveniji (ROSUS) · doi:10.18690/978-961-286-337-1.4
Koraki priprave 3D natisnjenega žilnega modela za namen načrtovanja operacije, z uporabo MR in CT slik pacienta z možgansko anevrizmo
Vovk, A. (2020) · Računalniška obdelava slik in njena uporaba v Sloveniji (ROSUS) · doi:10.18690/978-961-286-337-1.2
Latent Space Analysis of GANs for Controlled Face Deidentification
Pavlin, J., & Meden, B. (2020) · Računalniška obdelava slik in njena uporaba v Sloveniji (ROSUS) · doi:10.18690/978-961-286-337-1.9
ROSUS 2020 - Računalniška obdelava slik in njena uporaba v Sloveniji 2020: Zbornik 15. strokovne konference
Potočnik, B. (2020) · doi:10.18690/978-961-286-337-1
Semi-Supervised Graph Embedding via Multi-instance Kernel Learning
Wu, Z.-F., & Li, Y.-F. (2020) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp48618.2020.00-94
“Traditional supervised learning assumes that each training example is expressed as a vector, while multi-instance learning [16] [17] considers each training example to be expressed as a bag of instances.”
Background
Reduction Scheme for Empirical Risk Minimization and Its Applications to Multiple-Instance LearningPreprint
Suehiro, D., & Takimoto, E. (2019) · arXiv (Cornell University)
Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels?Preprint
Bian, T., Xiao, X., Xu, T., Rong, Y., Huang, W., Zhao, P., & Huang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.05970
“Another similar concept to our IGI is Multiple-Instance Learning (MIL) [11] that adopts global labels of bags to identify the labels of local instances.”
Generalisations of stochastic supervision models
Lu, X., Qiao, Y., Zhu, R., Wang, G., Ma, Z., & Xue, J. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107575
Healthism@MediaEval 2019 - Insights for Wellbeing Task: Factors Related to Subjective and Objective Health.
Huang, Q., Sheng, A., Pang, L., Wei, X.-Y., & Jain, R. (2019) · MediaEval
DCU-ADAPT at MediaEval 2019: Eyes and Ears Together.
Moriya, Y., & Jones, G. J. F. (2019) · MediaEval
Domain-Specific Lexical Grounding in Noisy Visual-Textual Documents
Yauney, G., Hessel, J., & Mimno, D. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.160
Feed-forward weakly supervised deep learning models for breast cancer diagnosis from histological images
Rony, J. (2020) · Espace ÉTS (ETS)
A Visual Mining Approach to Improved Multiple- Instance Learning
Castelo, S., Ponti, M. A., & Minghim, R. (2021) · Algorithms · doi:10.3390/a14120344
“Amongst the characteristics of problems that are ﬁt to be solved by MIL approaches are those in week supervision scenarios that do not work well with standard machine learning pipelines [10].”
Background
Learning with partially separable dataPreprint
Khozaei, A., Moradi, H., & Hosseini, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.06869
“So, they also assume the data, in bag level, is separable [20].”
Background
Supporting the Diagnosis of Dysplastic Nevi Syndrome via Multiple Instance Learning approaches.
Vocaturo, E., & Zumpano, E. (2020) · Archive of Doctoral Theses and Digital Collections (University of Calabria)
Dual Normalization Multitasking for Audio-Visual Sounding Object LocalizationPreprint
Nishikawa, T., Shimada, D., & Yokono, J. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.00180 · Cited by 1
“Many of the recent techniques[26, 2, 33, 36, 31, 28] use MIL, Class Activation Mapping (CAM) or attention to localize the sound source.”
MethodInfluential
AMIL:An attentional multi-instance learning for computer-aided diagnosis of skin diagnosis
Jin, M., Zhang, D., & Cao, P. (2020) · International Symposium on Image Computing and Digital Medicine (ISICDM) · doi:10.1145/3451421.3451459
“Instead, the origin pictures are cropped into patches, called a bag [9, 10].”
Background
ON THE USE OF MULTIPLE INSTANCE LEARNING FOR DATA CLASSIFICATION
Salih, N. Z., & Khalaf, W. (2021) · Journal of Engineering and Sustainable Development · doi:10.31272/jeasd.conf.2.1.15
Graph Convolution Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy VideosPreprint
Adewole, S., Fernandes, P., Jablonski, J. A., Copland, A. P., Porter, M. D., Syed, S., & Brown, D. E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09110
“The ﬁnal layer is a multiple-instance classiﬁer which is a fully connected layer that learns a multi-instance classiﬁcation [85] of the video.”
A Multiple Instance Learning Approach for the Automatic Classification of Skin Lesions (Discussion Paper).
Vocaturo, E., Zumpano, E., Giallombardo, G., & Miglionico, G. (2021) · SEBD

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