{"id":"W4224021932","doi":"10.48550/arxiv.2204.04944","title":"Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Point cloud; Segmentation; Computer science; Receptive field; Pyramid (geometry); Graph; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Representation (politics); Computer vision; Theoretical computer science; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001406324,0.0002588824,0.0002717917,0.0003171217,0.0001917479,0.0000540645,0.0001793711,0.0002001412,0.00003359562],"category_scores_gemma":[0.00001017309,0.0003209729,0.0001973505,0.000334401,0.0000377599,0.0001148286,0.0001403942,0.0003428643,0.000002939312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001660513,"about_ca_system_score_gemma":0.00002001455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007348792,"about_ca_topic_score_gemma":0.00007312158,"domain_scores_codex":[0.9990439,0.0000419095,0.0001468251,0.0004920868,0.00006422711,0.0002110934],"domain_scores_gemma":[0.9994298,0.00004795204,0.00009582049,0.0002800082,0.00006704478,0.00007934448],"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":[0.00002546236,0.00001529629,0.0009818863,0.0002622507,0.0002738665,0.00001506939,0.000197316,0.996706,0.0002570958,0.0001814268,0.0002057424,0.0008785716],"study_design_scores_gemma":[0.0004181423,0.00002122263,0.0001533976,0.00006794594,0.000437997,0.000001762549,0.0002898288,0.9877788,0.0004181717,0.01003303,0.000036586,0.0003431142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.502418,0.0002647122,0.4964025,0.00004403198,0.0002936529,0.0002388373,0.00003881914,0.0002361833,0.00006322211],"genre_scores_gemma":[0.9976189,0.0008050819,0.0006950825,0.00002554361,0.00005619792,0.000004316466,0.0004079981,0.00004361205,0.000343245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4957074,"threshold_uncertainty_score":0.9999242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02918292575007795,"score_gpt":0.1784559312344703,"score_spread":0.1492730054843923,"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."}}