{"id":"W4390872661","doi":"10.1109/iccv51070.2023.00086","title":"HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling","year":2023,"lang":"en","type":"article","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Set (abstract data type); Artificial intelligence; Deep learning; Active learning (machine learning); Training set; Deep neural networks; Machine learning; Artificial neural network","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":[0.003040927,0.002576649,0.001524176,0.002181974,0.0009874983,0.003507081,0.007119413,0.003808031,0.009973277],"category_scores_gemma":[0.00888312,0.002011236,0.002357878,0.001401955,0.002378371,0.00347188,0.006075209,0.004888905,0.005058323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001640954,"about_ca_system_score_gemma":0.001812292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00547809,"about_ca_topic_score_gemma":0.01610091,"domain_scores_codex":[0.997794,0.0004772959,0.0001051984,0.0006145462,0.0008510789,0.0001578936],"domain_scores_gemma":[0.9959441,0.001735473,0.0002169067,0.001462606,0.0004376778,0.0002032384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000578034,0.000321954,0.002474632,0.0005328309,0.0002462305,0.0002768025,0.0005885686,0.253857,0.02890195,0.02824273,0.04869106,0.6352881],"study_design_scores_gemma":[0.00003348653,0.00004125286,0.0001117967,0.00002880369,0.00001234294,0.00008878045,0.00003621873,0.9651496,0.01283723,0.01451853,0.007118664,0.00002319661],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002005559,0.00009401715,0.9850905,0.000106739,0.00004311013,0.00006492244,0.0003363219,0.01147398,0.0007848468],"genre_scores_gemma":[0.07273196,0.0001500522,0.9181454,0.0004628748,0.00004199516,0.000320531,0.002216572,0.003234139,0.00269641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009973277,"threshold_uncertainty_score":0.033364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02171627020064517,"score_gpt":0.2471518072096053,"score_spread":0.2254355370089602,"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."}}