{"id":"W4285223750","doi":"10.1007/978-3-031-06794-5_31","title":"A Multi-task Learning Framework for Semantic Segmentation in MLS Point Clouds","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Point cloud; Segmentation; Artificial intelligence; Correctness; Task (project management); Annotation; Artificial neural network; Point (geometry); Machine learning; Pattern recognition (psychology); Computer vision; Algorithm","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":[0.002087248,0.001344749,0.002252268,0.001699241,0.001146183,0.002423557,0.004041746,0.002985524,0.005588786],"category_scores_gemma":[0.002675435,0.001241224,0.002559518,0.002678724,0.0009594456,0.002707627,0.003211919,0.003068974,0.002942085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001324078,"about_ca_system_score_gemma":0.001969503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02173305,"about_ca_topic_score_gemma":0.02373694,"domain_scores_codex":[0.998834,0.0002257948,0.00007717793,0.0003673682,0.0003228472,0.0001729316],"domain_scores_gemma":[0.9990929,0.0003065468,0.00006039242,0.0001655523,0.0002979533,0.00007662962],"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":[0.0003168072,0.0002448851,0.0005025605,0.0001429421,0.0001598199,0.00009819711,0.00009678384,0.3254328,0.0112317,0.01210339,0.008527695,0.6411424],"study_design_scores_gemma":[0.000007243948,0.00002011726,0.0001048292,0.0000066741,0.000008834337,0.00001958744,0.000009260257,0.9920195,0.001370963,0.00545355,0.0009714534,0.000008131513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002011294,0.0001872318,0.9955622,0.00007495614,0.00003394745,0.00003667333,0.0001175666,0.001636309,0.0003397475],"genre_scores_gemma":[0.1020062,0.0003784451,0.8904563,0.0002331101,0.0001834849,0.0002533608,0.001669681,0.0006942138,0.004125216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02173305,"threshold_uncertainty_score":0.04321307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01553800010470076,"score_gpt":0.2630905159944634,"score_spread":0.2475525158897626,"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."}}