{"id":"W4393207075","doi":"10.1109/tgrs.2024.3381976","title":"Benchmarking Deep Learning Architectures for Urban Vegetation Point Cloud Semantic Segmentation From MLS","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Point cloud; Vegetation (pathology); Computer science; Segmentation; Image segmentation; Cloud computing; Artificial intelligence; Remote sensing; Deep learning; Computer vision; Geology","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":[0.001117752,0.002131068,0.0009727812,0.00153587,0.0005541159,0.001237527,0.002511362,0.001760802,0.003310608],"category_scores_gemma":[0.002406361,0.000566856,0.001539697,0.001810062,0.0006943793,0.00162867,0.00140784,0.001755106,0.00182717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002006505,"about_ca_system_score_gemma":0.001845282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04598274,"about_ca_topic_score_gemma":0.05685591,"domain_scores_codex":[0.999358,0.00009915108,0.00004467836,0.000225614,0.0001290322,0.0001435259],"domain_scores_gemma":[0.9994541,0.0001579247,0.00003782149,0.0001079737,0.0001875626,0.00005470552],"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":[0.0006309783,0.0004209158,0.008543643,0.0004115698,0.0003907825,0.0001857693,0.00009918964,0.7449949,0.004138667,0.001644323,0.0218707,0.2166687],"study_design_scores_gemma":[0.00002662925,0.00006271488,0.001303572,0.00002497139,0.00002155018,0.00002471956,0.00005405473,0.9944237,0.001953493,0.0008162441,0.001276952,0.00001143206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7761522,0.006552451,0.1543186,0.001627646,0.0007317228,0.0004396138,0.01390893,0.02915176,0.01711711],"genre_scores_gemma":[0.8602841,0.001098399,0.08959267,0.0005717971,0.00008619329,0.0002604913,0.04146559,0.0006729563,0.005967811],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04598274,"threshold_uncertainty_score":0.09143019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008528135576775672,"score_gpt":0.2360404611202845,"score_spread":0.2275123255435088,"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."}}