{"id":"W3120768806","doi":"10.48550/arxiv.2101.05036","title":"Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Correctness; Probabilistic logic; Minimum bounding box; Variance (accounting); Entropy (arrow of time); Regression; Scoring rule; Data mining; Statistics; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01392595,0.001933586,0.001675097,0.00206395,0.0005657295,0.002477724,0.002525303,0.002224268,0.001788269],"category_scores_gemma":[0.05937065,0.001002145,0.0008924578,0.001054156,0.002527422,0.005242448,0.003977924,0.003493586,0.0005774381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002397285,"about_ca_system_score_gemma":0.001325233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003085108,"about_ca_topic_score_gemma":0.003674605,"domain_scores_codex":[0.9941931,0.002125404,0.0002563406,0.0009803207,0.002102948,0.0003418081],"domain_scores_gemma":[0.9789212,0.01498999,0.001474752,0.0023168,0.001874652,0.0004225514],"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":[0.0002315581,0.00006619209,0.006777443,0.000118331,0.0001395734,0.00008022431,0.00007495413,0.894967,0.003930416,0.01459971,0.001869704,0.07714482],"study_design_scores_gemma":[0.000004736877,0.00003215763,0.0004983446,0.00002161099,0.000008501046,0.00002705734,0.00001075351,0.9828476,0.003697029,0.01258302,0.0002563012,0.00001281051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05722159,0.0005197951,0.937641,0.0005046511,0.00005102831,0.00007643655,0.000334589,0.002207764,0.001443197],"genre_scores_gemma":[0.8173819,0.000353037,0.1782173,0.0003918231,0.0000854528,0.000164984,0.001359195,0.0005813268,0.001464916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01392595,"threshold_uncertainty_score":0.07364827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05686327775697341,"score_gpt":0.2433853414853592,"score_spread":0.1865220637283858,"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."}}