{"id":"W3039470676","doi":"10.1186/s41074-020-00064-w","title":"Pseudo-labelling-aided semantic segmentation on sparsely annotated 3D point clouds","year":2020,"lang":"en","type":"article","venue":"IPSJ Transactions on Computer Vision and Applications","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Point cloud; Segmentation; Labelling; Artificial intelligence; Task (project management); Process (computing); Point (geometry); Pattern recognition (psychology); Machine learning","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":[0.00005787939,0.0001974896,0.0001920781,0.00012303,0.0002450081,0.00008801177,0.000103427,0.00006943198,0.00005810267],"category_scores_gemma":[7.722673e-7,0.0001911082,0.00008535591,0.0004336126,0.00002472483,0.00008525035,0.000003321619,0.0002288025,0.0002001105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002599798,"about_ca_system_score_gemma":0.000008283205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005641997,"about_ca_topic_score_gemma":0.000002424328,"domain_scores_codex":[0.9990268,0.00002558637,0.0002867838,0.0003353879,0.000163056,0.0001623241],"domain_scores_gemma":[0.9994904,0.00006178266,0.00003329917,0.000205834,0.00004670824,0.0001619286],"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":[0.00001385536,0.0001079718,0.000002704988,0.00003581374,0.00006255132,0.000001363746,0.0002575757,0.8499689,0.002844301,0.000103566,0.0003954358,0.146206],"study_design_scores_gemma":[0.0003908774,0.000137671,0.00003805512,0.00003720718,0.00006419395,0.000003485202,0.00003331769,0.9951513,0.002088407,0.0001048162,0.001751817,0.0001987837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02050072,0.00003872605,0.9770941,0.001327724,0.00006845669,0.0002719676,0.00003133928,0.0005156947,0.0001512462],"genre_scores_gemma":[0.9841201,0.0002252902,0.01449931,0.0008457491,0.0001171811,0.00007735444,0.00004567101,0.00003314749,0.00003613792],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9636194,"threshold_uncertainty_score":0.7793168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02463703088734011,"score_gpt":0.2380939537316931,"score_spread":0.213456922844353,"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."}}