{"id":"W4396934766","doi":"10.1007/s11263-024-02096-6","title":"Benchmarking Object Detection Robustness against Real-World Corruptions","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Benchmarking; Robustness (evolution); Artificial intelligence; Computer science; Pattern recognition (psychology); Object detection; Computer vision; Data mining","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004481417,0.001155554,0.001014978,0.001473411,0.0004166636,0.001327429,0.00131103,0.002342057,0.001928632],"category_scores_gemma":[0.02556768,0.0004385106,0.0008806739,0.0008618154,0.001407677,0.001291362,0.001825177,0.001159475,0.001010709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008314593,"about_ca_system_score_gemma":0.0007336079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002475483,"about_ca_topic_score_gemma":0.001176007,"domain_scores_codex":[0.9960444,0.001034998,0.0002681426,0.001017477,0.001091888,0.0005431487],"domain_scores_gemma":[0.9896398,0.005614665,0.0008627349,0.002126784,0.001417488,0.0003386601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001965689,0.0004721656,0.01020394,0.0003489126,0.000541825,0.0003348705,0.0001029816,0.7999775,0.0557799,0.003868418,0.004038687,0.1223651],"study_design_scores_gemma":[0.00004304223,0.0003882567,0.005727469,0.0000246848,0.00008137059,0.0002650126,0.0000318403,0.9451695,0.04549175,0.001728625,0.001019097,0.00002940361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6963939,0.001588827,0.2898442,0.0007123286,0.0005325794,0.0002006885,0.0009502086,0.004191675,0.005585522],"genre_scores_gemma":[0.9690788,0.0001612439,0.02779598,0.0001136522,0.00004039929,0.00003411591,0.001324394,0.0002243678,0.00122696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004481417,"threshold_uncertainty_score":0.0237003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01202882766508434,"score_gpt":0.3142536283562484,"score_spread":0.302224800691164,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}