{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008633969,0.0001946621,0.0002282511,0.001109245,0.0001398793,0.0009452959,0.001459274,0.00007200496,0.00003016593],"category_scores_gemma":[0.00004527172,0.0001731802,0.00025343,0.0006110765,0.00003998324,0.001838152,0.0004894832,0.0006406587,0.00002425675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003694281,"about_ca_system_score_gemma":0.000156483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000216658,"about_ca_topic_score_gemma":0.0000209471,"domain_scores_codex":[0.9975945,0.000170644,0.0006825143,0.0003322592,0.001007491,0.0002125472],"domain_scores_gemma":[0.9983066,0.0003928388,0.0003629595,0.0002386225,0.0005921703,0.0001068549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002813176,0.00004451919,0.0001505801,0.00001121832,0.0001078336,0.0005077037,0.0002563065,0.4068071,0.0008362487,0.004777624,0.0005886806,0.5858841],"study_design_scores_gemma":[0.000326879,0.0001854515,0.003438737,0.0005662661,0.00001470966,0.0004353389,0.000007266428,0.9849037,0.0002915869,0.000800845,0.00884928,0.0001799413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03039829,0.0001157259,0.9495378,0.001086414,0.01775724,0.00006690706,0.000001296555,0.0001608967,0.0008754965],"genre_scores_gemma":[0.8804057,0.0001007989,0.1157664,0.0001558816,0.003443792,0.000001508106,0.000004316406,0.00002002949,0.0001016054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8500074,"threshold_uncertainty_score":0.9115511,"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."}}