{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003476509,0.001019775,0.0008416573,0.001142993,0.0003666193,0.0009251173,0.001525259,0.001010978,0.00229869],"category_scores_gemma":[0.001286781,0.0004178179,0.0009002537,0.0009634642,0.0006600356,0.001595165,0.00138124,0.00111309,0.001091488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237749,"about_ca_system_score_gemma":0.001140431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01216467,"about_ca_topic_score_gemma":0.01668992,"domain_scores_codex":[0.9997138,0.0000302111,0.00001275746,0.0001013062,0.00008690667,0.00005496997],"domain_scores_gemma":[0.9996817,0.00008072408,0.00003435979,0.00007160192,0.00009395761,0.00003776227],"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":[0.0003213835,0.0001692017,0.001688897,0.0001176837,0.0001077411,0.0001910143,0.0001355242,0.4763348,0.05761978,0.01927442,0.006359045,0.4376805],"study_design_scores_gemma":[0.000004046241,0.0000179937,0.0001488262,0.000002431122,0.000005440754,0.00002282999,0.000008693206,0.9902939,0.004877996,0.004163868,0.0004497533,0.000004239693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03893565,0.0001341112,0.9553462,0.0001450052,0.00003278698,0.00004327044,0.00031883,0.003357231,0.001686846],"genre_scores_gemma":[0.5665494,0.0002058424,0.4251275,0.0002595407,0.00005239335,0.0001159167,0.002270787,0.0005090573,0.004909575],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01216467,"threshold_uncertainty_score":0.02418774,"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."}}