{"url":"/sota/anomaly-detection-on-road-anomaly","task":{"name":"Anomaly Detection","url":"/task/anomaly-detection","note":null},"dataset":{"name":"Road Anomaly","url":"/dataset/road-anomaly"},"category":"Computer Vision","categories":["Computer Vision","Graphs","Methodology","Miscellaneous"],"category_note":null,"description":"**Anomaly Detection** is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.\r\n\r\n[Image source]: [GAN-based Anomaly Detection in Imbalance Problems](https://paperswithcode.com/paper/gan-based-anomaly-detection-in-imbalance)","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":["AP","FPR95"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP":"higher","FPR95":null}},"counts":{"rows":10,"rows_with_code":9,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"OodDINO","metrics":{"AP":"95.21","FPR95":"2.11"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"RbA","metrics":{"AP":"90.28","FPR95":"4.92"},"uses_additional_data":true,"paper_date":"2022-11-25","paper":"/paper/pixels-together-strong-segmenting-unknown","paper_url":"https://arxiv.org/abs/2211.14293v2","paper_title":"RbA: Segmenting Unknown Regions Rejected by All","code":"https://github.com/NazirNayal8/RbA","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"DOoD","metrics":{"AP":"89.1","FPR95":"8.8"},"uses_additional_data":false,"paper_date":"2024-07-22","paper":"/paper/diffusion-for-out-of-distribution-detection","paper_url":"https://arxiv.org/abs/2407.15739v1","paper_title":"Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond","code":"https://github.com/lmb-freiburg/diffusion-for-ood","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"cDNP","metrics":{"AP":"85.6","FPR95":"9.8"},"uses_additional_data":false,"paper_date":"2022-11-12","paper":"/paper/far-away-in-the-deep-space-nearest-neighbor","paper_url":"https://arxiv.org/abs/2211.06660v2","paper_title":"Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection","code":"https://github.com/silviogalesso/dense-ood-knns","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Mask2Anomaly","metrics":{"AP":"79.70","FPR95":"13.45"},"uses_additional_data":true,"paper_date":"2023-07-25","paper":"/paper/unmasking-anomalies-in-road-scene","paper_url":"https://arxiv.org/abs/2307.13316v1","paper_title":"Unmasking Anomalies in Road-Scene Segmentation","code":"https://github.com/shyam671/mask2anomaly-unmasking-anomalies-in-road-scene-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"RPL+CoroCL","metrics":{"AP":"71.61","FPR95":"17.74"},"uses_additional_data":true,"paper_date":"2022-11-26","paper":"/paper/residual-pattern-learning-for-pixel-wise-out","paper_url":"https://arxiv.org/abs/2211.14512v3","paper_title":"Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation","code":"https://github.com/yyliu01/rpl","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":7,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"PEBAL","metrics":{"AP":"45.10","FPR95":"44.58"},"uses_additional_data":true,"paper_date":"2021-11-24","paper":"/paper/pixel-wise-energy-biased-abstention-learning","paper_url":"https://arxiv.org/abs/2111.12264v6","paper_title":"Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes","code":"https://github.com/tianyu0207/pebal","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":8,"model":"Synboost","metrics":{"AP":"41.83","FPR95":"59.72"},"uses_additional_data":true,"paper_date":"2021-03-09","paper":"/paper/pixel-wise-anomaly-detection-in-complex","paper_url":"https://arxiv.org/abs/2103.05445v1","paper_title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","code":"https://github.com/giandbt/synboost","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"SML","metrics":{"AP":"25.82","FPR95":"49.74"},"uses_additional_data":false,"paper_date":"2021-07-23","paper":"/paper/standardized-max-logits-a-simple-yet","paper_url":"https://arxiv.org/abs/2107.11264v4","paper_title":"Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation","code":"https://github.com/shjung13/standardized-max-logits","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SynthCP","metrics":{"AP":"24.86","FPR95":"64.69"},"uses_additional_data":true,"paper_date":"2020-03-18","paper":"/paper/synthesize-then-compare-detecting-failures","paper_url":"https://arxiv.org/abs/2003.08440v2","paper_title":"Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation","code":"https://github.com/YingdaXia/SynthCP","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":0}}],"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":5,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":13,"n_unverified":19,"n_samples":32,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":13,"n_unverified":19,"n_samples":32,"n_pointer_only_licence":3,"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"}}}