{"id":"W4386245243","doi":"10.1109/crv60082.2023.00035","title":"HyperMODEST: Self-Supervised 3D Object Detection with Confidence Score Filtering","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Object detection; Artificial intelligence; Object (grammar); Precision and recall; Code (set theory); Process (computing); Filter (signal processing); Recall; Range (aeronautics); Baseline (sea); Low Confidence; Detector; F1 score; Machine learning; Pattern recognition (psychology); Computer vision","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008265959,0.0001279658,0.0001044609,0.00009027843,0.000209821,0.00009368209,0.0005302664,0.00003312689,0.00001099084],"category_scores_gemma":[0.000009550622,0.0001057709,0.00002504928,0.001300689,0.00002791987,0.0005348097,0.0001900075,0.0001105605,0.0002505262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003432181,"about_ca_system_score_gemma":0.00003119315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001587718,"about_ca_topic_score_gemma":0.00004575727,"domain_scores_codex":[0.998911,0.00002228476,0.0001335631,0.0004356555,0.0002068092,0.0002906489],"domain_scores_gemma":[0.9991118,0.0001119722,0.00004200866,0.0005930508,0.00006028255,0.00008084842],"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":[0.00004729531,0.0001332116,0.002087318,0.0001043645,0.00008001521,0.000132147,0.002056352,0.07344,0.3765456,0.06411891,0.0007253196,0.4805294],"study_design_scores_gemma":[0.0002143873,0.00009302469,0.002827161,0.00002055332,0.000004810941,0.00007442898,0.00002212791,0.963629,0.03025791,0.001946932,0.0006737242,0.0002359223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1115139,0.00000926191,0.8841355,0.0002245818,0.00007825111,0.0002484441,5.454175e-7,0.002085433,0.00170412],"genre_scores_gemma":[0.8774561,0.00002415043,0.1218384,0.000208992,0.00004757686,0.0001162778,0.00000177346,0.00001422778,0.0002925019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.890189,"threshold_uncertainty_score":0.4313211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02601647411069827,"score_gpt":0.2462329755890092,"score_spread":0.2202165014783109,"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."}}