{"url":"/sota/robust-object-detection-on-dwd","task":{"name":"Robust Object Detection","url":"/task/robust-object-detection","note":null},"dataset":{"name":"DWD","url":"/dataset/dwd"},"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 [AP50]"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mPC [AP50]":null}},"counts":{"rows":12,"rows_with_code":11,"rows_with_paper_page":12,"rows_dated":12,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GDD (SD-1.5 Backbone)","metrics":{"mPC [AP50]":"40.5"},"uses_additional_data":false,"paper_date":"2025-03-03","paper":"/paper/generalized-diffusion-detector-mining-robust","paper_url":"https://arxiv.org/abs/2503.02101v1","paper_title":"Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection","code":"https://github.com/heboyong/Generalized-Diffusion-Detector","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"GDD (R101, Faster RCNN)","metrics":{"mPC [AP50]":"38.1"},"uses_additional_data":false,"paper_date":"2025-03-03","paper":"/paper/generalized-diffusion-detector-mining-robust","paper_url":"https://arxiv.org/abs/2503.02101v1","paper_title":"Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection","code":"https://github.com/heboyong/Generalized-Diffusion-Detector","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"PhysAug","metrics":{"mPC [AP50]":"37.5"},"uses_additional_data":false,"paper_date":"2024-12-16","paper":"/paper/physaug-a-physical-guided-and-frequency-based","paper_url":"https://arxiv.org/abs/2412.11807v1","paper_title":"PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection","code":"https://github.com/startracker0/physaug","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"VLTDet","metrics":{"mPC [AP50]":"36.9"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/vltseg-simple-transfer-of-clip-based-vision","paper_url":"https://arxiv.org/abs/2312.02021v4","paper_title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","code":"https://github.com/VLTSeg/VLTSeg","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"OA-DG","metrics":{"mPC [AP50]":"31.8"},"uses_additional_data":false,"paper_date":"2023-12-19","paper":"/paper/object-aware-domain-generalization-for-object","paper_url":"https://arxiv.org/abs/2312.12133v1","paper_title":"Object-Aware Domain Generalization for Object Detection","code":"https://github.com/WoojuLee24/OA-DG","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"SRCD","metrics":{"mPC [AP50]":"29.6"},"uses_additional_data":false,"paper_date":"2023-07-04","paper":"/paper/srcd-semantic-reasoning-with-compound-domains","paper_url":"https://arxiv.org/abs/2307.01750v2","paper_title":"SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"CDSD","metrics":{"mPC [AP50]":"28.7"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/single-domain-generalized-object-detection-in","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Wu_Single-Domain_Generalized_Object_Detection_in_Urban_Scene_via_Cyclic-Disentangled_Self-Distillation_CVPR_2022_paper.html","paper_title":"Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation","code":"https://github.com/amingwu/single-dgod","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"SHADE","metrics":{"mPC [AP50]":"28.4"},"uses_additional_data":false,"paper_date":"2022-04-06","paper":"/paper/style-hallucinated-dual-consistency-learning","paper_url":"https://arxiv.org/abs/2204.02548v2","paper_title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","code":"https://github.com/helioszhao/shade","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"ISW","metrics":{"mPC [AP50]":"26.3"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/robustnet-improving-domain-generalization-in","paper_url":"https://arxiv.org/abs/2103.15597v2","paper_title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","code":"https://github.com/shachoi/RobustNet","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SW","metrics":{"mPC [AP50]":"26.1"},"uses_additional_data":false,"paper_date":"2019-04-22","paper":"/paper/switchable-whitening-for-deep-representation","paper_url":"https://arxiv.org/abs/1904.09739v4","paper_title":"Switchable Whitening for Deep Representation Learning","code":"https://github.com/XingangPan/Switchable-Whitening","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":8,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"IBN-Net","metrics":{"mPC [AP50]":"25.5"},"uses_additional_data":false,"paper_date":"2018-07-25","paper":"/paper/two-at-once-enhancing-learning-and","paper_url":"https://arxiv.org/abs/1807.09441v3","paper_title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","code":"https://github.com/layumi/Person_reID_baseline_pytorch","n_code_links":25,"syntology":{"n_ran":4,"n_unverified":12,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"IterNorm","metrics":{"mPC [AP50]":"23.4"},"uses_additional_data":false,"paper_date":"2019-04-06","paper":"/paper/iterative-normalization-beyond","paper_url":"http://arxiv.org/abs/1904.03441v1","paper_title":"Iterative Normalization: Beyond Standardization towards Efficient Whitening","code":"https://github.com/XingangPan/Switchable-Whitening","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":11,"n_samples":14,"n_pointer_only_licence":1}}],"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":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":13,"n_unverified":31,"n_samples":44,"n_pointer_only_licence":2,"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":31,"n_samples":44,"n_pointer_only_licence":2,"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"}}}