{"url":"/sota/out-of-distribution-detection-on-cifar-10-vs","task":{"name":"Out-of-Distribution Detection","url":"/task/out-of-distribution-detection","note":null},"dataset":{"name":"CIFAR-10 vs CIFAR-100","url":"/dataset/cifar-10"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Detect out-of-distribution or anomalous examples.","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":["AUROC","AUPR","FPR95"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AUROC":null,"AUPR":null,"FPR95":null}},"counts":{"rows":14,"rows_with_code":12,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"DHM","metrics":{"AUPR":"100","AUROC":"100"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/deep-hybrid-models-for-out-of-distribution","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Cao_Deep_Hybrid_Models_for_Out-of-Distribution_Detection_CVPR_2022_paper.html","paper_title":"Deep Hybrid Models for Out-of-Distribution Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"R+ViT finetuned on CIFAR-10","metrics":{"AUPR":"97.75","AUROC":"98.52"},"uses_additional_data":true,"paper_date":"2021-06-06","paper":"/paper/exploring-the-limits-of-out-of-distribution","paper_url":"https://arxiv.org/abs/2106.03004v3","paper_title":"Exploring the Limits of Out-of-Distribution Detection","code":"https://github.com/stanislavfort/exploring_the_limits_of_OOD_detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"ViT finetuned on CIFAR-10","metrics":{"AUPR":"97.68","AUROC":"98.42"},"uses_additional_data":true,"paper_date":"2021-06-06","paper":"/paper/exploring-the-limits-of-out-of-distribution","paper_url":"https://arxiv.org/abs/2106.03004v3","paper_title":"Exploring the Limits of Out-of-Distribution Detection","code":"https://github.com/stanislavfort/exploring_the_limits_of_OOD_detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"MLP-Mixer finetuned on CIFAR-10","metrics":{"AUPR":"96.28","AUROC":"97.85"},"uses_additional_data":true,"paper_date":"2021-06-06","paper":"/paper/exploring-the-limits-of-out-of-distribution","paper_url":"https://arxiv.org/abs/2106.03004v3","paper_title":"Exploring the Limits of Out-of-Distribution Detection","code":"https://github.com/stanislavfort/exploring_the_limits_of_OOD_detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Forte","metrics":{"AUPR":" 09.69 ± 01.08","AUROC":"97.63 ± 00.15"},"uses_additional_data":false,"paper_date":"2024-10-02","paper":"/paper/forte-finding-outliers-with-representation","paper_url":"https://arxiv.org/abs/2410.01322v2","paper_title":"Forte : Finding Outliers with Representation Typicality Estimation","code":"https://github.com/DebarghaG/forte","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"ZODE-KNN","metrics":{"AUROC":"97.12","FPR95":"18.29"},"uses_additional_data":false,"paper_date":"2022-12-24","paper":"/paper/boosting-out-of-distribution-detection-with-1","paper_url":"https://arxiv.org/abs/2212.12720v2","paper_title":"Boosting Out-of-Distribution Detection with Multiple Pre-trained Models","code":"https://github.com/mapleleaf6/zode","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"OpenHybrid","metrics":{"AUROC":"95.1"},"uses_additional_data":false,"paper_date":"2020-03-27","paper":"/paper/hybrid-models-for-open-set-recognition","paper_url":"https://arxiv.org/abs/2003.12506v2","paper_title":"Hybrid Models for Open Set Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"ERD (ResNet18)","metrics":{"AUROC":"95.1"},"uses_additional_data":true,"paper_date":"2020-12-10","paper":"/paper/learn-what-you-can-t-learn-regularized-1","paper_url":"https://arxiv.org/abs/2012.05825v3","paper_title":"Semi-supervised novelty detection using ensembles with regularized disagreement","code":"https://github.com/ericpts/reto","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Wide 40-2 + OECC","metrics":{"AUPR":"82.0","AUROC":"94.9"},"uses_additional_data":true,"paper_date":"2019-06-08","paper":"/paper/simultaneous-classification-and-novelty","paper_url":"https://arxiv.org/abs/1906.03509v4","paper_title":"Outlier Exposure with Confidence Control for Out-of-Distribution Detection","code":"https://github.com/nazim1021/OOD-detection-using-OECC","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"WRN 40-2 + OE","metrics":{"AUPR":"76.2","AUROC":"93.3"},"uses_additional_data":true,"paper_date":"2018-12-11","paper":"/paper/deep-anomaly-detection-with-outlier-exposure","paper_url":"http://arxiv.org/abs/1812.04606v3","paper_title":"Deep Anomaly Detection with Outlier Exposure","code":"https://github.com/hendrycks/outlier-exposure","n_code_links":9,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":4}},{"rank_in_archive_order":11,"model":"Isolation Forest on EfficientNet Softmax values","metrics":{"AUROC":"91.95"},"uses_additional_data":false,"paper_date":"2021-08-18","paper":"/paper/out-of-distribution-detection-using-outlier","paper_url":"https://arxiv.org/abs/2108.08218v2","paper_title":"Out-of-Distribution Detection Using Outlier Detection Methods","code":"https://github.com/jandiers/ood-detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"WRN 40-2 + Rotation Prediction","metrics":{"AUPR":"67.7","AUROC":"90.9"},"uses_additional_data":false,"paper_date":"2019-06-28","paper":"/paper/using-self-supervised-learning-can-improve","paper_url":"https://arxiv.org/abs/1906.12340v2","paper_title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","code":"https://github.com/hendrycks/ss-ood","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"WRN 40-2 (MSP Baseline)","metrics":{"AUPR":"55.8","AUROC":"87.9"},"uses_additional_data":false,"paper_date":"2016-10-07","paper":"/paper/a-baseline-for-detecting-misclassified-and","paper_url":"http://arxiv.org/abs/1610.02136v3","paper_title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","code":"https://github.com/hendrycks/error-detection","n_code_links":14,"syntology":{"n_ran":7,"n_unverified":14,"n_samples":21,"n_pointer_only_licence":6}},{"rank_in_archive_order":14,"model":"ResNet + diagonal elements of Gram matrix","metrics":{"AUROC":"79.7"},"uses_additional_data":false,"paper_date":"2019-12-28","paper":"/paper/detecting-out-of-distribution-examples-with","paper_url":"https://arxiv.org/abs/1912.12510v2","paper_title":"Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices","code":"https://github.com/nazim1021/OOD-detection-using-OECC","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":22,"n_unverified":24,"n_samples":46,"n_pointer_only_licence":18,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":22,"n_unverified":24,"n_samples":46,"n_pointer_only_licence":18,"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"}}}