{"id":"W4389246202","doi":"10.1111/phor.12468","title":"Weakly supervised semantic segmentation of mobile laser scanning point clouds via category balanced random annotation and deep consistency‐guided self‐distillation mechanism","year":2023,"lang":"en","type":"article","venue":"The Photogrammetric Record","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Point cloud; Computer science; Consistency (knowledge bases); Artificial intelligence; Distillation; Annotation; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009382295,0.001336112,0.00116422,0.001299213,0.000716457,0.00126046,0.002940818,0.001525362,0.001390951],"category_scores_gemma":[0.002218796,0.0006348,0.001326001,0.001087439,0.001173251,0.001940211,0.002098515,0.001857008,0.0008964433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001240943,"about_ca_system_score_gemma":0.00182302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01692004,"about_ca_topic_score_gemma":0.02037705,"domain_scores_codex":[0.9990307,0.0001490749,0.00004305403,0.0003741907,0.0002660851,0.0001368865],"domain_scores_gemma":[0.9991773,0.0001788902,0.0001133674,0.0002036718,0.0002617126,0.0000650059],"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":[0.0004284657,0.0002141966,0.00378918,0.0001606163,0.0001172155,0.0001718241,0.0002628439,0.6527871,0.03171021,0.006438483,0.005375779,0.2985441],"study_design_scores_gemma":[0.000005405013,0.00001698682,0.0002286436,0.00000413079,0.000004745763,0.00001160575,0.00001352007,0.9941593,0.003724206,0.001468214,0.0003568476,0.000006381593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09303398,0.0002770633,0.8972552,0.0003165262,0.00005895936,0.0001108894,0.0006273038,0.006705819,0.001614167],"genre_scores_gemma":[0.7095106,0.0001605512,0.2818047,0.0003521893,0.00006349363,0.0002097816,0.00382742,0.0004893955,0.003581824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01692004,"threshold_uncertainty_score":0.03364307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01260460535770155,"score_gpt":0.2393994724688147,"score_spread":0.2267948671111131,"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."}}