{"url":"/sota/robust-object-detection-on-coco","task":{"name":"Robust Object Detection","url":"/task/robust-object-detection","note":null},"dataset":{"name":"COCO (Common Objects in Context)","url":"/dataset/coco"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"A Benchmark for the: \r\nRobustness of Object Detection Models to Image Corruptions and Distortions\r\n\r\nTo allow fair comparison of robustness enhancing methods all models have to use a standard ResNet50 backbone because performance strongly scales with backbone capacity. If requested an unrestricted category can be added later.\r\n\r\nBenchmark Homepage: https://github.com/bethgelab/robust-detection-benchmark\r\n\r\n\r\nMetrics:\r\n\r\nmPC [AP]: Mean Performance under Corruption [measured in AP]\r\n\r\nrPC [%]: Relative Performance under Corruption [measured in %]\r\n\r\nTest sets:\r\nCoco: val 2017; Pascal VOC: test 2007; Cityscapes: val;\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Benchmarking Robustness in Object Detection](https://arxiv.org/pdf/1907.07484v1.pdf) )</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":["mPC [AP]","rPC [%]"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mPC [AP]":"higher","rPC [%]":null}},"counts":{"rows":2,"rows_with_code":2,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Faster R-CNN with Stylized Training Data","metrics":{"mPC [AP]":"20.4","rPC [%]":"58.9"},"uses_additional_data":false,"paper_date":"2019-07-17","paper":"/paper/benchmarking-robustness-in-object-detection","paper_url":"https://arxiv.org/abs/1907.07484v2","paper_title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","code":"https://github.com/bethgelab/imagecorruptions","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Faster R-CNN","metrics":{"mPC [AP]":"18.2","rPC [%]":"50.2"},"uses_additional_data":false,"paper_date":"2019-07-17","paper":"/paper/benchmarking-robustness-in-object-detection","paper_url":"https://arxiv.org/abs/1907.07484v2","paper_title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","code":"https://github.com/bethgelab/imagecorruptions","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}}],"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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0,"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"}}}