{"id":"W4393074218","doi":"10.1007/s41095-022-0311-7","title":"Active self-training for weakly supervised 3D scene semantic segmentation","year":2024,"lang":"en","type":"article","venue":"Computational Visual Media","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Shenzhen Science and Technology Innovation Program; Department of Education of Guangdong Province; Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Training (meteorology); Computer science; Segmentation; Artificial intelligence; Computer graphics; Computer vision; Natural language processing; Computer graphics (images); Pattern recognition (psychology); Geography","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":[0.0001140517,0.0001338068,0.0001516211,0.0001755569,0.00006934779,0.00008114349,0.00006127937,0.00005073623,0.0000381139],"category_scores_gemma":[0.00003203149,0.0001384391,0.00008923848,0.0002378886,0.00001326805,0.0001473038,0.00001024309,0.00009605107,0.00005998269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007974618,"about_ca_system_score_gemma":0.00005737761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001980104,"about_ca_topic_score_gemma":0.000002824384,"domain_scores_codex":[0.9991871,0.00001541396,0.0002017819,0.0001966714,0.0002176266,0.0001814423],"domain_scores_gemma":[0.9993519,0.000445353,0.00001315255,0.00004275577,0.00007677041,0.00007007826],"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":[0.000009328498,0.00002760923,0.00002068651,0.0002495617,0.00030544,0.00000611613,0.006286877,0.8744728,0.001788985,0.0002655477,0.0004457921,0.1161212],"study_design_scores_gemma":[0.0002187546,0.00002557415,0.0002473143,0.00007994285,0.00009148236,0.000003015015,0.0004060263,0.9963963,0.0004807592,0.001808236,0.00008656694,0.0001560391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.284463,0.00038457,0.7134694,0.00009805815,0.0006074614,0.0001451544,0.00004100065,0.0006557142,0.0001356268],"genre_scores_gemma":[0.9606847,0.00001582815,0.03830181,0.00004529711,0.0003942776,0.00004657555,0.0004546448,0.00003991942,0.00001691862],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6762218,"threshold_uncertainty_score":0.5645384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0303957873809121,"score_gpt":0.2973853097170243,"score_spread":0.2669895223361122,"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."}}