{"url":"/task/robust-object-detection","name":"Robust Object Detection","slug":"robust-object-detection","description_markdown":"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>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":90,"papers_with_code":50,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/robust-object-detection-on-cityscapes-1","slug":"robust-object-detection-on-cityscapes-1","dataset":"Cityscapes","dataset_url":"/dataset/cityscapes","rows_in_archive":13,"metrics":["mPC [AP]"],"first_row_in_archive_order":{"model":"FGT (SD-1.5 Backbone)","paper_title":"Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability","paper_url":"/paper/boosting-domain-generalized-and-adaptive","paper_date":"2025-06-26","arxiv_id":"2506.21042","code_links":[{"title":"heboyong/fitness-generalization-transferability","url":"https://github.com/heboyong/fitness-generalization-transferability"}],"syntology":null}},{"leaderboard":"/sota/robust-object-detection-on-dwd","slug":"robust-object-detection-on-dwd","dataset":"DWD","dataset_url":"/dataset/dwd","rows_in_archive":12,"metrics":["mPC [AP50]"],"first_row_in_archive_order":{"model":"GDD (SD-1.5 Backbone)","paper_title":"Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection","paper_url":"/paper/generalized-diffusion-detector-mining-robust","paper_date":"2025-03-03","arxiv_id":"2503.02101","code_links":[{"title":"heboyong/Generalized-Diffusion-Detector","url":"https://github.com/heboyong/Generalized-Diffusion-Detector"}],"syntology":null}},{"leaderboard":"/sota/robust-object-detection-on-cityscapes","slug":"robust-object-detection-on-cityscapes","dataset":"Cityscapes test","dataset_url":"/dataset/cityscapes","rows_in_archive":2,"metrics":["mPC [AP]","rPC [%]"],"first_row_in_archive_order":{"model":"Faster R-CNN with Stylized Training Data","paper_title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","paper_url":"/paper/benchmarking-robustness-in-object-detection","paper_date":"2019-07-17","arxiv_id":"1907.07484","code_links":[{"title":"bethgelab/imagecorruptions","url":"https://github.com/bethgelab/imagecorruptions"},{"title":"bethgelab/robust-detection-benchmark","url":"https://github.com/bethgelab/robust-detection-benchmark"},{"title":"bethgelab/stylize-datasets","url":"https://github.com/bethgelab/stylize-datasets"},{"title":"bethgelab/mmdetection","url":"https://github.com/bethgelab/mmdetection"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/robust-object-detection-on-coco","slug":"robust-object-detection-on-coco","dataset":"COCO (Common Objects in Context)","dataset_url":"/dataset/coco","rows_in_archive":2,"metrics":["mPC [AP]","rPC [%]"],"first_row_in_archive_order":{"model":"Faster R-CNN with Stylized Training Data","paper_title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","paper_url":"/paper/benchmarking-robustness-in-object-detection","paper_date":"2019-07-17","arxiv_id":"1907.07484","code_links":[{"title":"bethgelab/imagecorruptions","url":"https://github.com/bethgelab/imagecorruptions"},{"title":"bethgelab/robust-detection-benchmark","url":"https://github.com/bethgelab/robust-detection-benchmark"},{"title":"bethgelab/stylize-datasets","url":"https://github.com/bethgelab/stylize-datasets"},{"title":"bethgelab/mmdetection","url":"https://github.com/bethgelab/mmdetection"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/robust-object-detection-on-pascal-voc-2007","slug":"robust-object-detection-on-pascal-voc-2007","dataset":"PASCAL VOC 2007","dataset_url":"/dataset/pascal-voc-2007","rows_in_archive":2,"metrics":["mPC [AP50]","rPC [%]"],"first_row_in_archive_order":{"model":"Faster R-CNN with Stylized Training Data","paper_title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","paper_url":"/paper/benchmarking-robustness-in-object-detection","paper_date":"2019-07-17","arxiv_id":"1907.07484","code_links":[{"title":"bethgelab/imagecorruptions","url":"https://github.com/bethgelab/imagecorruptions"},{"title":"bethgelab/robust-detection-benchmark","url":"https://github.com/bethgelab/robust-detection-benchmark"},{"title":"bethgelab/stylize-datasets","url":"https://github.com/bethgelab/stylize-datasets"},{"title":"bethgelab/mmdetection","url":"https://github.com/bethgelab/mmdetection"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/pascal-voc-2007","name":"PASCAL VOC 2007","full_name":"PASCAL VOC 2007","num_papers_in_archive":126},{"url":"/dataset/dwd","name":"DWD","full_name":"Diverse Weather Dataset","num_papers_in_archive":12},{"url":"/dataset/rf100","name":"RF100","full_name":"Roboflow 100","num_papers_in_archive":5},{"url":"/dataset/separated-coco","name":"Separated COCO","full_name":"","num_papers_in_archive":4},{"url":"/dataset/aircraft-context-dataset","name":"Aircraft Context Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/occluded-coco","name":"Occluded COCO","full_name":"","num_papers_in_archive":2},{"url":"/dataset/apron-dataset","name":"Apron Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":50,"tagged_in_all":90,"items":[{"url":"/paper/yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","arxiv_id":"1804.02767","repositories_listed":311,"syntology":{"n":124,"n_ran":18,"n_unverified":106,"n_pointer_only":19}},{"url":"/paper/faster-r-cnn-towards-real-time-object","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","date":"2015-06-04","arxiv_id":"1506.01497","repositories_listed":196,"syntology":{"n":124,"n_ran":59,"n_unverified":65,"n_pointer_only":42}},{"url":"/paper/two-at-once-enhancing-learning-and","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","date":"2018-07-25","arxiv_id":"1807.09441","repositories_listed":25,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/random-erasing-data-augmentation","title":"Random Erasing Data Augmentation","date":"2017-08-16","arxiv_id":"1708.04896","repositories_listed":18,"syntology":null},{"url":"/paper/augmix-a-simple-data-processing-method-to","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","date":"2019-12-05","arxiv_id":"1912.02781","repositories_listed":15,"syntology":{"n":51,"n_ran":43,"n_unverified":8,"n_pointer_only":25}},{"url":"/paper/domain-adaptive-faster-r-cnn-for-object","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","date":"2018-03-08","arxiv_id":"1803.03243","repositories_listed":8,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":4}},{"url":"/paper/learning-data-augmentation-strategies-for","title":"Learning Data Augmentation Strategies for Object Detection","date":"2019-06-26","arxiv_id":"1906.11172","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/iterative-normalization-beyond","title":"Iterative Normalization: Beyond Standardization towards Efficient Whitening","date":"2019-04-06","arxiv_id":"1904.03441","repositories_listed":5,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":1}},{"url":"/paper/benchmarking-robustness-in-object-detection","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","date":"2019-07-17","arxiv_id":"1907.07484","repositories_listed":4,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/robust-object-detection-of-underwater-robot","title":"Robust Object Detection of Underwater Robot based on Domain Generalization","date":"2025-03-18","arxiv_id":"2503.19929","repositories_listed":2,"syntology":null},{"url":"/paper/dyra-dynamic-resolution-adjustment-for-scale","title":"DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors","date":"2023-11-28","arxiv_id":"2311.17098","repositories_listed":2,"syntology":null},{"url":"/paper/style-hallucinated-dual-consistency-learning","title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","date":"2022-04-06","arxiv_id":"2204.02548","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/simrod-a-simple-adaptation-method-for-robust","title":"SimROD: A Simple Adaptation Method for Robust Object Detection","date":"2021-07-28","arxiv_id":"2107.13389","repositories_listed":2,"syntology":null},{"url":"/paper/robustnet-improving-domain-generalization-in","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","date":"2021-03-29","arxiv_id":"2103.15597","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tog-targeted-adversarial-objectness-gradient","title":"TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems","date":"2020-04-09","arxiv_id":"2004.04320","repositories_listed":2,"syntology":null},{"url":"/paper/delving-into-robust-object-detection-from","title":"Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach","date":"2019-08-11","arxiv_id":"1908.03856","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/boosting-domain-generalized-and-adaptive","title":"Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability","date":"2025-06-26","arxiv_id":"2506.21042","repositories_listed":1,"syntology":null},{"url":"/paper/llm-empowered-embodied-agent-for-memory","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","date":"2025-04-30","arxiv_id":"2504.21716","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/generalized-diffusion-detector-mining-robust","title":"Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection","date":"2025-03-03","arxiv_id":"2503.02101","repositories_listed":1,"syntology":null},{"url":"/paper/physaug-a-physical-guided-and-frequency-based","title":"PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection","date":"2024-12-16","arxiv_id":"2412.11807","repositories_listed":1,"syntology":null},{"url":"/paper/robosense-large-scale-dataset-and-benchmark","title":"RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments","date":"2024-08-28","arxiv_id":"2408.15503","repositories_listed":1,"syntology":null},{"url":"/paper/semanticspray-a-multimodal-dataset-for","title":"SemanticSpray++: A Multimodal Dataset for Autonomous Driving in Wet Surface Conditions","date":"2024-06-14","arxiv_id":"2406.09945","repositories_listed":1,"syntology":null},{"url":"/paper/constscene-dataset-and-model-for-advancing","title":"ConstScene: Dataset and Model for Advancing Robust Semantic Segmentation in Construction Environments","date":"2023-12-27","arxiv_id":"2312.16516","repositories_listed":1,"syntology":null},{"url":"/paper/object-aware-domain-generalization-for-object","title":"Object-Aware Domain Generalization for Object Detection","date":"2023-12-19","arxiv_id":"2312.12133","repositories_listed":1,"syntology":null},{"url":"/paper/vltseg-simple-transfer-of-clip-based-vision","title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","date":"2023-12-04","arxiv_id":"2312.02021","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-robustness-of-object-detection-models","title":"On the Robustness of Object Detection Models on Aerial Images","date":"2023-08-29","arxiv_id":"2308.15378","repositories_listed":1,"syntology":null},{"url":"/paper/improved-region-proposal-network-for-enhanced","title":"Improved Region Proposal Network for Enhanced Few-Shot Object Detection","date":"2023-08-15","arxiv_id":"2308.07535","repositories_listed":1,"syntology":null},{"url":"/paper/coco-o-a-benchmark-for-object-detectors-under-1","title":"COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts","date":"2023-07-24","arxiv_id":"2307.12730","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-importance-of-backbone-to-the","title":"On the Importance of Backbone to the Adversarial Robustness of Object Detectors","date":"2023-05-27","arxiv_id":"2305.17438","repositories_listed":1,"syntology":null},{"url":"/paper/mind-the-backbone-minimizing-backbone","title":"Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection","date":"2023-03-26","arxiv_id":"2303.14744","repositories_listed":1,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}