{"url":"/sota/multiple-instance-learning-on-camelyon16","task":{"name":"Multiple Instance Learning","url":"/task/multiple-instance-learning","note":null},"dataset":{"name":"CAMELYON16","url":"/dataset/camelyon16"},"category":"Methodology","categories":["Methodology"],"category_note":null,"description":"**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>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AUC","ACC","Expected Calibration Error","FROC","Patch AUC"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AUC":"higher","ACC":"higher","Expected Calibration Error":"lower","FROC":null,"Patch AUC":"higher"}},"counts":{"rows":14,"rows_with_code":14,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Snuffy (DINO Exhaustive)","metrics":{"ACC":"0.948","AUC":"0.987","Expected Calibration Error":"0.083","FROC":"0.675","Patch AUC":"0.957"},"uses_additional_data":false,"paper_date":"2024-08-15","paper":"/paper/snuffy-efficient-whole-slide-image-classifier","paper_url":"https://arxiv.org/abs/2408.08258v3","paper_title":"Snuffy: Efficient Whole Slide Image Classifier","code":"https://github.com/jafarinia/snuffy","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Snuffy (SimCLR Exhaustive)","metrics":{"ACC":"0.952","AUC":"0.970","Expected Calibration Error":"0.057","FROC":"0.622","Patch AUC":"0.980"},"uses_additional_data":false,"paper_date":"2024-08-15","paper":"/paper/snuffy-efficient-whole-slide-image-classifier","paper_url":"https://arxiv.org/abs/2408.08258v3","paper_title":"Snuffy: Efficient Whole Slide Image Classifier","code":"https://github.com/jafarinia/snuffy","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CAMIL","metrics":{"ACC":"0.917","AUC":"0.959"},"uses_additional_data":false,"paper_date":"2023-05-09","paper":"/paper/camil-context-aware-multiple-instance","paper_url":"https://arxiv.org/abs/2305.05314v3","paper_title":"CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images","code":"https://github.com/olgarithmics/ICLR_CAMIL","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CAMIL (CAMIL-L)","metrics":{"ACC":"0.91","AUC":"0.953"},"uses_additional_data":false,"paper_date":"2023-05-09","paper":"/paper/camil-context-aware-multiple-instance","paper_url":"https://arxiv.org/abs/2305.05314v3","paper_title":"CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images","code":"https://github.com/olgarithmics/ICLR_CAMIL","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CAMIL (CAMIL-G)","metrics":{"ACC":"0.891","AUC":"0.95"},"uses_additional_data":false,"paper_date":"2023-05-09","paper":"/paper/camil-context-aware-multiple-instance","paper_url":"https://arxiv.org/abs/2305.05314v3","paper_title":"CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images","code":"https://github.com/olgarithmics/ICLR_CAMIL","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DTFD-MIL (AFS)","metrics":{"ACC":"0.908","AUC":"0.946"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/dtfd-mil-double-tier-feature-distillation","paper_url":"https://arxiv.org/abs/2203.12081v1","paper_title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","code":"https://github.com/hrzhang1123/dtfd-mil","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":7,"model":"DTFD-MIL (MAS)","metrics":{"ACC":"0.897","AUC":"0.945"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/dtfd-mil-double-tier-feature-distillation","paper_url":"https://arxiv.org/abs/2203.12081v1","paper_title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","code":"https://github.com/hrzhang1123/dtfd-mil","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":8,"model":"DTFD-MIL (MaxMinS)","metrics":{"ACC":"0.899","AUC":"0.941"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/dtfd-mil-double-tier-feature-distillation","paper_url":"https://arxiv.org/abs/2203.12081v1","paper_title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","code":"https://github.com/hrzhang1123/dtfd-mil","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":9,"model":"TransMIL","metrics":{"ACC":"0.8837","AUC":"0.9309"},"uses_additional_data":false,"paper_date":"2021-06-02","paper":"/paper/transmil-transformer-based-correlated","paper_url":"https://arxiv.org/abs/2106.00908v2","paper_title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","code":"https://github.com/szc19990412/TransMIL","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"DSMIL-LC","metrics":{"ACC":"0.8992","AUC":"0.9165"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/dual-stream-multiple-instance-learning","paper_url":"https://arxiv.org/abs/2011.08939v3","paper_title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","code":"https://github.com/binli123/dsmil-wsi","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Snuffy (MAE Adapter)","metrics":{"ACC":"0.900","AUC":"0.910","Expected Calibration Error":"0.078","FROC":"0.543","Patch AUC":"0.873"},"uses_additional_data":false,"paper_date":"2024-08-15","paper":"/paper/snuffy-efficient-whole-slide-image-classifier","paper_url":"https://arxiv.org/abs/2408.08258v3","paper_title":"Snuffy: Efficient Whole Slide Image Classifier","code":"https://github.com/jafarinia/snuffy","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"DTFD-MIL (MaxS)","metrics":{"ACC":"0.864","AUC":"0.907"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/dtfd-mil-double-tier-feature-distillation","paper_url":"https://arxiv.org/abs/2203.12081v1","paper_title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","code":"https://github.com/hrzhang1123/dtfd-mil","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":13,"model":"DSMIL","metrics":{"ACC":"0.8682","AUC":"0.8944"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/dual-stream-multiple-instance-learning","paper_url":"https://arxiv.org/abs/2011.08939v3","paper_title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","code":"https://github.com/binli123/dsmil-wsi","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"DGMIL","metrics":{"ACC":"0.8018","AUC":"0.8368"},"uses_additional_data":false,"paper_date":"2022-06-17","paper":"/paper/dgmil-distribution-guided-multiple-instance","paper_url":"https://arxiv.org/abs/2206.08861v1","paper_title":"DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification","code":"https://github.com/miccaiif/dgmil","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":19,"n_unverified":20,"n_samples":39,"n_pointer_only_licence":15,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}