{"url":"/task/multiple-instance-learning","name":"Multiple Instance Learning","slug":"multiple-instance-learning","description_markdown":"**Multiple Instance Learning** is a type of weakly supervised learning algorithm where training data is arranged in bags, where each bag contains a set of instances $X=\\\\{x_1,x_2, \\ldots,x_M\\\\}$, and there is one single label $Y$ per bag, $Y\\in\\\\{0, 1\\\\}$ in the case of a binary classification problem. It is assumed that individual labels $y_1, y_2,\\ldots, y_M$ exist for the instances within a bag, but they are unknown during training. In the standard Multiple Instance assumption, a bag is considered negative if all its instances are negative. On the other hand, a bag is positive, if at least one instance in the bag is positive.\n\n\n<span class=\"description-source\">Source: [Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification ](https://arxiv.org/abs/1812.11560)</span>","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":744,"papers_with_code":322,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":13,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/multiple-instance-learning-on-camelyon16","slug":"multiple-instance-learning-on-camelyon16","dataset":"CAMELYON16","dataset_url":"/dataset/camelyon16","rows_in_archive":14,"metrics":["AUC","ACC","Expected Calibration Error","FROC","Patch AUC"],"first_row_in_archive_order":{"model":"Snuffy (DINO Exhaustive)","paper_title":"Snuffy: Efficient Whole Slide Image Classifier","paper_url":"/paper/snuffy-efficient-whole-slide-image-classifier","paper_date":"2024-08-15","arxiv_id":"2408.08258","code_links":[{"title":"jafarinia/snuffy","url":"https://github.com/jafarinia/snuffy"}],"syntology":null}},{"leaderboard":"/sota/multiple-instance-learning-on-tcga","slug":"multiple-instance-learning-on-tcga","dataset":"TCGA","dataset_url":"/dataset/tcga","rows_in_archive":8,"metrics":["ACC","AUC"],"first_row_in_archive_order":{"model":"DTFD-MIL (AFS)","paper_title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","paper_url":"/paper/dtfd-mil-double-tier-feature-distillation","paper_date":"2022-03-22","arxiv_id":"2203.12081","code_links":[{"title":"hrzhang1123/dtfd-mil","url":"https://github.com/hrzhang1123/dtfd-mil"},{"title":"liupei101/psemix","url":"https://github.com/liupei101/psemix"}],"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":3}}},{"leaderboard":"/sota/multiple-instance-learning-on-elephant","slug":"multiple-instance-learning-on-elephant","dataset":"Elephant","dataset_url":"/dataset/elephant","rows_in_archive":2,"metrics":["AUC","ACC"],"first_row_in_archive_order":{"model":"Snuffy","paper_title":"Snuffy: Efficient Whole Slide Image Classifier","paper_url":"/paper/snuffy-efficient-whole-slide-image-classifier","paper_date":"2024-08-15","arxiv_id":"2408.08258","code_links":[{"title":"jafarinia/snuffy","url":"https://github.com/jafarinia/snuffy"}],"syntology":null}},{"leaderboard":"/sota/multiple-instance-learning-on-musk-v1","slug":"multiple-instance-learning-on-musk-v1","dataset":"Musk v1","dataset_url":"/dataset/musk-v1","rows_in_archive":2,"metrics":["ACC","AUC"],"first_row_in_archive_order":{"model":"Snuffy","paper_title":"Snuffy: Efficient Whole Slide Image Classifier","paper_url":"/paper/snuffy-efficient-whole-slide-image-classifier","paper_date":"2024-08-15","arxiv_id":"2408.08258","code_links":[{"title":"jafarinia/snuffy","url":"https://github.com/jafarinia/snuffy"}],"syntology":null}},{"leaderboard":"/sota/multiple-instance-learning-on-musk-v2","slug":"multiple-instance-learning-on-musk-v2","dataset":"Musk v2","dataset_url":"/dataset/musk-v2","rows_in_archive":2,"metrics":["ACC","AUC"],"first_row_in_archive_order":{"model":"DSMIL","paper_title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","paper_url":"/paper/dual-stream-multiple-instance-learning","paper_date":"2020-11-17","arxiv_id":"2011.08939","code_links":[{"title":"binli123/dsmil-wsi","url":"https://github.com/binli123/dsmil-wsi"},{"title":"Xiyue-Wang/RetCCL","url":"https://github.com/Xiyue-Wang/RetCCL"}],"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/camelyon16","name":"CAMELYON16","full_name":"Cancer Metastases in Lymph Nodes Challenge 2016","num_papers_in_archive":172},{"url":"/dataset/ucf-crime","name":"UCF-Crime","full_name":"","num_papers_in_archive":142},{"url":"/dataset/ave","name":"AVE","full_name":"Audio-Visual Event Localization","num_papers_in_archive":103},{"url":"/dataset/elephant","name":"Elephant","full_name":"","num_papers_in_archive":47},{"url":"/dataset/tcga","name":"TCGA","full_name":"The Cancer Genome Atlas","num_papers_in_archive":23},{"url":"/dataset/daisee","name":"DAiSEE","full_name":"","num_papers_in_archive":17},{"url":"/dataset/musk-v1","name":"Musk v1","full_name":"Musk v1","num_papers_in_archive":4},{"url":"/dataset/musk-v2","name":"Musk v2","full_name":"Musk v2","num_papers_in_archive":4},{"url":"/dataset/spot","name":"SPOT","full_name":"Sentiment Polarity Annotations Dataset","num_papers_in_archive":3},{"url":"/dataset/colorectal-adenoma","name":"Colorectal Adenoma","full_name":"","num_papers_in_archive":2},{"url":"/dataset/wiki-en","name":"Wiki-en","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/wiki-zh","name":"Wiki-zh","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/camnuvem-dataset","name":"CamNuvem Dataset","full_name":"CamNuvem: A Robbery Dataset for Video Anomaly Detection","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":322,"tagged_in_all":744,"items":[{"url":"/paper/attention-based-deep-multiple-instance","title":"Attention-based Deep Multiple Instance Learning","date":"2018-02-13","arxiv_id":"1802.04712","repositories_listed":17,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/set-transformer-a-framework-for-attention","title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks","date":"2018-10-01","arxiv_id":"1810.00825","repositories_listed":9,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/real-world-anomaly-detection-in-surveillance","title":"Real-world Anomaly Detection in Surveillance Videos","date":"2018-01-12","arxiv_id":"1801.04264","repositories_listed":9,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/falformer-feature-aware-landmarks-self","title":"FALFormer: Feature-aware Landmarks self-attention for Whole-slide Image Classification","date":"2024-07-10","arxiv_id":"2407.07340","repositories_listed":5,"syntology":null},{"url":"/paper/pcl-proposal-cluster-learning-for-weakly","title":"PCL: Proposal Cluster Learning for Weakly Supervised Object Detection","date":"2018-07-09","arxiv_id":"1807.03342","repositories_listed":4,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/multiple-instance-detection-network-with","title":"Multiple Instance Detection Network with Online Instance Classifier Refinement","date":"2017-04-01","arxiv_id":"1704.00138","repositories_listed":4,"syntology":null},{"url":"/paper/adr-attention-diversification-regularization","title":"AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification","date":"2024-06-18","arxiv_id":"2406.15303","repositories_listed":3,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":12}},{"url":"/paper/timemil-advancing-multivariate-time-series","title":"TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning","date":"2024-05-06","arxiv_id":"2405.03140","repositories_listed":3,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/point-to-box-network-for-accurate-object","title":"Point-to-Box Network for Accurate Object Detection via Single Point Supervision","date":"2022-07-14","arxiv_id":"2207.06827","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/transmil-transformer-based-correlated","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","date":"2021-06-02","arxiv_id":"2106.00908","repositories_listed":3,"syntology":null},{"url":"/paper/weakly-supervised-video-anomaly-detection","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","date":"2021-01-25","arxiv_id":"2101.10030","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/hopfield-networks-is-all-you-need","title":"Hopfield Networks is All You Need","date":"2020-07-16","arxiv_id":"2008.02217","repositories_listed":3,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/multiple-anchor-learning-for-visual-object","title":"Multiple Anchor Learning for Visual Object Detection","date":"2019-12-04","arxiv_id":"1912.02252","repositories_listed":3,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/camel-a-weakly-supervised-learning-framework","title":"CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation","date":"2019-08-28","arxiv_id":"1908.10555","repositories_listed":3,"syntology":null},{"url":"/paper/multiple-instance-choquet-integral-classifier","title":"Multiple Instance Choquet Integral Classifier Fusion and Regression for Remote Sensing Applications","date":"2018-03-11","arxiv_id":"1803.04048","repositories_listed":3,"syntology":null},{"url":"/paper/using-neural-network-formalism-to-solve","title":"Using Neural Network Formalism to Solve Multiple-Instance Problems","date":"2016-09-23","arxiv_id":"1609.07257","repositories_listed":3,"syntology":null},{"url":"/paper/revisiting-end-to-end-learning-with-slide","title":"Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology","date":"2025-06-03","arxiv_id":"2506.02408","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":9}},{"url":"/paper/xmil-insightful-explanations-for-multiple","title":"xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology","date":"2024-06-06","arxiv_id":"2406.04280","repositories_listed":2,"syntology":null},{"url":"/paper/morphological-prototyping-for-unsupervised","title":"Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology","date":"2024-05-19","arxiv_id":"2405.11643","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":9}},{"url":"/paper/mambamil-enhancing-long-sequence-modeling","title":"MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology","date":"2024-03-11","arxiv_id":"2403.06800","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/feature-re-embedding-towards-foundation-model","title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","date":"2024-02-27","arxiv_id":"2402.17228","repositories_listed":2,"syntology":{"n":24,"n_ran":13,"n_unverified":11,"n_pointer_only":24}},{"url":"/paper/shapley-values-enabled-progressive-pseudo-bag","title":"Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification","date":"2023-12-09","arxiv_id":"2312.05490","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-multiple-instance-learning-for-1","title":"Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher","date":"2023-12-02","arxiv_id":"2312.01099","repositories_listed":2,"syntology":null},{"url":"/paper/clip-tsa-clip-assisted-temporal-self","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","date":"2022-12-09","arxiv_id":"2212.05136","repositories_listed":2,"syntology":null},{"url":"/paper/multiple-instance-learning-via-iterative-self","title":"Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning","date":"2022-10-17","arxiv_id":"2210.09452","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/remix-a-general-and-efficient-framework-for","title":"ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification","date":"2022-07-05","arxiv_id":"2207.01805","repositories_listed":2,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-via","title":"Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning","date":"2022-06-22","arxiv_id":"2206.11011","repositories_listed":2,"syntology":null},{"url":"/paper/dtfd-mil-double-tier-feature-distillation","title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","date":"2022-03-22","arxiv_id":"2203.12081","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/object-localization-under-single-coarse-point","title":"Object Localization under Single Coarse Point Supervision","date":"2022-03-17","arxiv_id":"2203.09338","repositories_listed":2,"syntology":null},{"url":"/paper/explainable-multiple-abnormality","title":"Explainable multiple abnormality classification of chest CT volumes","date":"2021-11-24","arxiv_id":"2111.12215","repositories_listed":2,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}