{"id":"W4366999266","doi":"10.48550/arxiv.2304.11207","title":"SSS3D: Fast Neural Architecture Search For Efficient Three-Dimensional Semantic Segmentation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Point (geometry); Artificial intelligence; Artificial neural network; Sampling (signal processing); Architecture; Space (punctuation); Data mining; Pattern recognition (psychology); Computer vision; Mathematics; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.0007012475,0.001588447,0.00103129,0.001179317,0.0007147776,0.001232342,0.002049156,0.001725985,0.007605863],"category_scores_gemma":[0.001813336,0.0008021593,0.001291262,0.0008876882,0.0008453215,0.001477612,0.001862195,0.001345422,0.001449189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001603233,"about_ca_system_score_gemma":0.002214657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01062596,"about_ca_topic_score_gemma":0.02599916,"domain_scores_codex":[0.9997124,0.00006621004,0.00001141167,0.00006284491,0.0001053218,0.00004167254],"domain_scores_gemma":[0.999639,0.0001634234,0.00002812376,0.00005132927,0.00008157539,0.00003649884],"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":[0.0001970654,0.00007224715,0.0009714896,0.0001667726,0.000126476,0.00009756152,0.00009209742,0.8137172,0.005224003,0.01786032,0.01209526,0.1493795],"study_design_scores_gemma":[0.00001350128,0.00001283866,0.0000422526,0.000004341372,0.000004017242,0.00001091508,0.000009325521,0.994473,0.0006703578,0.003881038,0.0008749621,0.000003366848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0270166,0.0003947827,0.9587423,0.0002906285,0.00007045965,0.0001227076,0.000655833,0.006044589,0.00666221],"genre_scores_gemma":[0.2324506,0.0001888585,0.7601234,0.0002492272,0.00004195902,0.0003485816,0.00165926,0.0009322052,0.004005994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01062596,"threshold_uncertainty_score":0.02544409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08338999105381895,"score_gpt":0.2399904191099797,"score_spread":0.1566004280561607,"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."}}