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 accessOverview
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
Cites
Statistics
Verification
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“With over 30 billion sequences in total, this represents one of the largest multiple instance learning experiments ever conducted (Carbonneau et al., 2018).”
From Hopfield Networks is All You Need (2020) · cites this paper as Carbonneau et al., 2018
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
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.”
MethodGreedy 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.”
MethodThe 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.”
MethodStatistical 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].”
MethodBeyond 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
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
Cited by
Sorted by citations
Items 701–734 of 734
Dual-Granularity Labeling for Multi-Instance Multi-Label Data With Skewed Annotation
Zhang, X., Luo, T., & Hou, C. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3705259
“On the one hand, there is standard assumption that the bag contains at [5].”
Hassanieh, W., Oyewole, I., Samaha, P., Kalach, F. E., Harik, R., & Chehade, A. (2026) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2026.06.017
Onozato, Y., Sakairi, Y., Kawana, H., Yamamoto, T., Iwata, T., Araki, A., Itami, M., Kawakami, E., & Suzuki, H. (2026) · Modern Pathology · doi:10.1016/j.modpat.2026.101035
Liu, Z. H., Shen, J., Cui, L., Xu, M., Zhu, X., & Shi, X. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104202
Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
Tang, W., Yang, Y., Zhang, W., & Zhang, M.-L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3712701
“Multi-instance learning (MIL), initially developed for drug activity prediction [20], has since been applied across diverse fields, including text classification [21], [22], [23], object detection [24], and video anomaly detection [25].”
Defect-Aware Multi-View Adaptive Alignment for defect inspection in target-scarce domain adaptation
Kim, S., Park, B., Chae, D., & Joung, J. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105071
Uncertainty-aware multi-instance partial-label learning via evidential deep model
Jie, G., Wang, F., Song, G., Lin, L., Yu, Y., & Zheng, Q. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134578
Chen, J., Couetil, J. L., Maher, N. G., Scolyer, R. A., Alomari, A. K., Huang, K., & Zhang, J. (2026) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3807503.3819367
“Multiple-instancelearning(MIL)hasbeenwidelyadoptedforwhole-slideimage(WSI)analysis,whereslide-levelpredictionsareob-tainedbyaggregatingpatch-levelinformationwithoutrequiring patch-levelannotations[2,5,9].”
Boosting EEG emotion recognition: A multi-dataset study of MIL-augmented XGBoost classifiers
Daşdemir, Y., & Sezgin, İ. C. (2026) · DÜMF Mühendislik Dergisi · doi:10.24012/dumf.1939758
“In contrast, the collective assumption [6] posits that the bag label reflects the combined contribution of all instances, none of which is individually decisive.”
Nemoto, M., Niwa, Y., Sahara, J., Nagaoka, T., Mikami, K., Kimura, Y., Tanaka, A., Kenmochi⋆, Y., Passat, N., Kaida, H., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31927-2_41
Emotion recognition from body movement through interpretable motion-aware sequential modeling
Esteban-Romero, S., Martín-Fernández, I., San-Segundo, R., Gil-Martín, M., & Fernández-Martínez, F. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1897208
“MIL is a weakly supervised learning framework commonly applied when the training data are organized into sets, known as bags, and labels are only available at the bag level, while the individual instances contained in each bag remain unlabeled (Carbonneau et al., 2018).”
Koyun, O. C., Guo, Y., Lü, H., Demir, M. F., Alili, A., Rahoui, N., Cardona, D., & Gürcan, M. N. (2026) · Cancers · doi:10.3390/cancers18162540
“Most WSI models use multiple-instance learning (MIL), in which patches are treated as instances and aggregated into a slide-level representation [6].”
Petitpas, Y., Benlala, I., Baldacci, F., Dournes, G., Jaunas, K., Clin, B., Brochard, P., Gislard, A., Delva, F., Lacourt, A., et al. (2026) · Diagnostics · doi:10.3390/diagnostics16162519
“This formulation naturally enables the application of a Multiple Instance Learning (MIL) framework [20] to infer patient-level PP presence status from PP-level features.”
Pourreza, A., Noble, M. R., Shamir, Y., Atsmon, G., Lati, R. N., Eizenberg, H., & Mesgaran, M. B. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7347387
Guo, J., Zhang, K., Jiang, K., Deng, R., & Guo, B. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7351946
Multi-instance multi-label learning: Theory, taxonomy, and modern methods—A critical survey
Ahmed, S. U., Tahir, M. A., & Sheikh, M. W. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134896
A Systematic Bibliometric Review of Artificial Intelligence and Information Literacy Research
Κουτσουπιάς, Ν., & Nosios, M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7262-4.ch001
TandemNet: A Multi-Scale Multiple-Instance Learning Framework for Early-Season Rice Yield Prediction
Zeng, M., Wu, W., Yang, R., Zhang, W., Du, S., Huang, X., & Liu, L. (2026) · Remote Sensing · doi:10.3390/rs18173040
ClinIAN: Clinically Informed Attention Network
König, F., Ditz, J. C., Shamsara, E., Hedberg, P., Fanti, I., Nauclér, P., Carioti, L., Walker, A., Parczewski, M., Drobniewski, F. A., et al. (2026) · Bioinformatics Advances · doi:10.1093/bioadv/vbag254
A Gradient-Level Diagnosis of Extreme Class Imbalance in Multiple Instance Learning via q-Calculus
Rehman, A. A., Baro, E. N., & Otero, P. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8090282
Cui, Y., Ren, X., Wang, L., Zhu, H., Shen, Z., & Zhao, C. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3734980
“Restrictions apply. and requires only bag labels instead of instance-level labels, where a positive bag contains at least one target instance, and a negative bag consists entirely of background instances [13].”
Behavioral Featurization for Data of Unknown or Volatile Dimensionality
Lemos, F. A. D. L., do Amaral, D., Priotto, F. M., & Lazzaretti, A. E. (2026) · IEEE Access · doi:10.1109/access.2026.3733861
“The nearest paradigm on the unknown-cardinality axis is multiple-instance learning (MIL), in which each example is a bag of a variable number of instances and only the bag carries a label [30], [31].”
Hu, T., Luan, H., Hu, J., Li, H., Pei, Y., Yang, K., Li, R., Niu, B., Chi, X., Jiang, J., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38470-6_51
Quality-Gated Episode-Level RGB-D Body Condition Scoring in Beef Cattle
Hou, Z., Cao, W., He, W., Yanwen, L. I., Li, J., Wu, D., Wang, R., & Yang, H. (2026) · Animals · doi:10.3390/ani16193040
“Unlike conventional approaches based on single-frame image classification, this study defined the RGB-D video segment collected from the same animal during one continuous acquisition process as an Episode and aggregated multiple instances using Attention-MIL [18,19].”
Lesion-Aware Multiple-Instance Learning for Grapevine Disease Recognition from Field RGB Images
Öztürk, Ö., Canbula, B., Özacar, T., & Ozacar, V. (2026) · Sensors · doi:10.3390/s26196318
Zhu, J., Liu, C., Zou, L., Xu, R., Xie, X., Ye, T., Zhang, L. J., & Zhang, B. (2026) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.70588
An Augmentation-based ConvNeXtV2-Femto Framework for BI-RADS Classification
Le-Ho, H.-K., Ngo, B.-V., Nguyen, T.-T., & Nguyen, T.-H. (2026) · International Conference on Green Technology and Sustainable Development (GTSD) · doi:10.1109/gtsd70918.2026.11722391
“In breast cancer image classification, the Otsu method is often applied to optimally determine the feature regions, forming the basis for ROI extraction [8].”
Makama, M. F., & Thango, B. A. (2026) · Batteries · doi:10.3390/batteries12100431
Wang, N., Zhang, K., Sonde, M., & Sheng, V. S. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00687-w
“However, in many real-world tasks, discriminative evidence may be distributed across multiple instances, and the dependencies among instances may also contribute to bag-level prediction (Carbonneau et al. 2018).”
Gacheva, I., Lu, D., Kurz, G., Triesch, J., Hattingen, E., & Polomac, N. (2026) · Neuroimage Reports · doi:10.1016/j.ynirp.2026.100418
“The multiple instance learning approach (Dietterich et al., 1997; Carbonneau et al., 2018; Campanella et al., 2019) proved essential for handling the inherent ambiguity in patient-level labeling of individual spectra.”
Partially privacy-protected logistic regression with L1 penalty and sign constraint
Kim, H., Choi, H., & Lee, W. (2026) · AStA Advances in Statistical Analysis · doi:10.1007/s10182-026-00572-7
Triplet-Propagated Kernel Mapping for Multiple-Instance Learning from Triplet Comparison Bags
Yuan, M., Sun, Y., Jin, S., Wang, T., & Xu, F. (2026) · International Conference on Artificial Intelligence Technologies and Applications (ICAITA) · doi:10.1109/icaita71179.2026.11737107
Entropy-Based Metrics for Evaluating Supervised Machine Learning Models: A Scoping Review
Çadırcı, M. S. (2026) · Cumhuriyet Science Journal · doi:10.17776/csj.1933076
Boosting the Performance of Evolutionary Multi-Instance Classification with Transfer Learning
Omri, N., Elarbi, M., Bechikh, S., & Coello, C. A. C. (2026) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec69861.2026.11727281
Metadata
- Authors
- Carbonneau, M.-A., Cheplygina, V., Granger, E., & Gagnon, G.
- Affiliations
- École de Technologie Supérieure (CA)
- Erasmus MC (NL)
- Corresponding author
- Carbonneau, Marc-André
- Venue
- Pattern Recognition
- Publisher
- Elsevier BV
- Published
- 2018-05
- Volume
- 77
- Pages
- 329-353
- ISSN
- 0031-3203 (ISSN-L)
- 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
- 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
