{"id":"W4408779932","doi":"10.1109/tnnls.2025.3543620","title":"SDSimPoint: Shallow-Deep Similarity Learning for Few-Shot Point Cloud Semantic Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Similarity (geometry); Artificial intelligence; Point cloud; Shot (pellet); Segmentation; Semantic similarity; Computer science; Cloud computing; Point (geometry); Natural language processing; Pattern recognition (psychology); Image (mathematics); Mathematics; Chemistry; Geometry","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":[0.0005568956,0.001475566,0.001517326,0.001397628,0.0004987674,0.001036599,0.003808749,0.001799907,0.003271258],"category_scores_gemma":[0.001980363,0.0006942075,0.001164552,0.001656468,0.0006149861,0.002722366,0.002522181,0.001970559,0.001439694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00119995,"about_ca_system_score_gemma":0.001473794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01213227,"about_ca_topic_score_gemma":0.01718863,"domain_scores_codex":[0.9994579,0.0000414603,0.00002393233,0.0002355447,0.0001520578,0.00008915315],"domain_scores_gemma":[0.9996064,0.00007645792,0.000047276,0.0001104056,0.0001102717,0.00004915851],"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":[0.0004231516,0.0004263018,0.003088703,0.0002796444,0.0002566127,0.000187392,0.0001807973,0.2113989,0.02368773,0.004968799,0.01669495,0.7384071],"study_design_scores_gemma":[0.00001442861,0.00006272682,0.0006025831,0.000009100368,0.0000140739,0.00006103626,0.00002384213,0.9890381,0.004821828,0.00415322,0.001185567,0.00001343409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04025975,0.0006613811,0.9452896,0.0001848816,0.0001175972,0.0001707003,0.001139891,0.0106205,0.001555657],"genre_scores_gemma":[0.5568062,0.0005265185,0.4245406,0.0005439476,0.0001120543,0.0003352019,0.009536687,0.0006747774,0.006923929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01213227,"threshold_uncertainty_score":0.02412331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01953940008850967,"score_gpt":0.2401650304456845,"score_spread":0.2206256303571749,"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."}}