{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/benchmarking-robustness-in-object-detection","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","arxiv_id":"1907.07484","date":"2019-07-17","proceeding":null,"authors":["Claudio Michaelis","Benjamin Mitzkus","Robert Geirhos","Evgenia Rusak","Oliver Bringmann","Alexander S. Ecker","Matthias Bethge","Wieland Brendel"],"abstract":"The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets, termed Pascal-C, Coco-C and Cityscapes-C, contain a large variety of image corruptions. We show that a range of standard object detection models suffer a severe performance loss on corrupted images (down to 30--60\\% of the original performance). However, a simple data augmentation trick---stylizing the training images---leads to a substantial increase in robustness across corruption type, severity and dataset. We envision our comprehensive benchmark to track future progress towards building robust object detection models. Benchmark, code and data are publicly available.","url_abs":"https://arxiv.org/abs/1907.07484v2","url_pdf":"https://arxiv.org/pdf/1907.07484v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"benchmarking-robustness-in-object-detection","repo_url":"https://github.com/bethgelab/mmdetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"benchmarking-robustness-in-object-detection","repo_url":"https://github.com/bethgelab/imagecorruptions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"benchmarking-robustness-in-object-detection","repo_url":"https://github.com/bethgelab/robust-detection-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"benchmarking-robustness-in-object-detection","repo_url":"https://github.com/bethgelab/stylize-datasets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"robust-object-detection","task_name":"Robust Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/robust-object-detection-on-coco","task":"Robust Object Detection","dataset":"COCO (Common Objects in Context)","model":"Faster R-CNN with Stylized Training Data","rank_in_archive_order":1,"of":2,"metrics":{"mPC [AP]":"20.4","rPC [%]":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-coco","task":"Robust Object Detection","dataset":"COCO (Common Objects in Context)","model":"Faster R-CNN","rank_in_archive_order":2,"of":2,"metrics":{"mPC [AP]":"18.2","rPC [%]":"50.2"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-cityscapes-1","task":"Robust Object Detection","dataset":"Cityscapes","model":"Stylized Training Data","rank_in_archive_order":9,"of":13,"metrics":{"mPC [AP]":"17.2"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-cityscapes","task":"Robust Object Detection","dataset":"Cityscapes test","model":"Faster R-CNN with Stylized Training Data","rank_in_archive_order":1,"of":2,"metrics":{"mPC [AP]":"17.2","rPC [%]":"47.4"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-cityscapes","task":"Robust Object Detection","dataset":"Cityscapes test","model":"Faster R-CNN","rank_in_archive_order":2,"of":2,"metrics":{"mPC [AP]":"12.2","rPC [%]":"33.4"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-pascal-voc-2007","task":"Robust Object Detection","dataset":"PASCAL VOC 2007","model":"Faster R-CNN with Stylized Training Data","rank_in_archive_order":1,"of":2,"metrics":{"mPC [AP50]":"56.2","rPC [%]":"69.9"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-pascal-voc-2007","task":"Robust Object Detection","dataset":"PASCAL VOC 2007","model":"Faster R-CNN","rank_in_archive_order":2,"of":2,"metrics":{"mPC [AP50]":"48.6","rPC [%]":"60.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.07484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.07484"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bethgelab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bethgelab/imagecorruptions","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bethgelab/robust-detection-benchmark","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bethgelab/stylize-datasets","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9f1bb16740f8d1ed","entry":"clipped_zoom","repo":"bethgelab/imagecorruptions","repo_kind":"official","path":"imagecorruptions/corruptions.py","file_url":"https://github.com/bethgelab/imagecorruptions/blob/HEAD/imagecorruptions/corruptions.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f1bb16740f8d1ed"}},{"code_sha256_prefix":"33492980f6e79af5","entry":"plasma_fractal","repo":"bethgelab/imagecorruptions","repo_kind":"official","path":"imagecorruptions/corruptions.py","file_url":"https://github.com/bethgelab/imagecorruptions/blob/HEAD/imagecorruptions/corruptions.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"33492980f6e79af5"}},{"code_sha256_prefix":"d76f63e8bd69d6b6","entry":"get_coco_style_results","repo":"bethgelab/robust-detection-benchmark","repo_kind":"official","path":"data-analysis/robustness_eval.py","file_url":"https://github.com/bethgelab/robust-detection-benchmark/blob/HEAD/data-analysis/robustness_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d76f63e8bd69d6b6"}},{"code_sha256_prefix":"736f6acb4c7f3097","entry":"get_results","repo":"bethgelab/robust-detection-benchmark","repo_kind":"official","path":"data-analysis/robustness_eval.py","file_url":"https://github.com/bethgelab/robust-detection-benchmark/blob/HEAD/data-analysis/robustness_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"736f6acb4c7f3097"}},{"code_sha256_prefix":"d7b21a2a720fbd2b","entry":"get_voc_style_results","repo":"bethgelab/robust-detection-benchmark","repo_kind":"official","path":"data-analysis/robustness_eval.py","file_url":"https://github.com/bethgelab/robust-detection-benchmark/blob/HEAD/data-analysis/robustness_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7b21a2a720fbd2b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}