{"id":"W4308085167","doi":"10.1109/cases55004.2022.00024","title":"Work-in-Progress: SuperNAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pascal (unit); Segmentation; FLOPS; Pareto principle; Training set; Pareto optimal; Machine learning; Artificial intelligence; Architecture; Set (abstract data type); Multi-objective optimization; Data mining; Pattern recognition (psychology); Parallel computing; Mathematical optimization; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002161649,0.0001529621,0.0001479769,0.0001702015,0.0003276152,0.00007323379,0.0008274611,0.00002655732,0.00004380591],"category_scores_gemma":[0.000007842176,0.0001495519,0.00006637265,0.001114222,0.00005293389,0.0002439927,0.0005111977,0.0002861065,0.00001337523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001681731,"about_ca_system_score_gemma":0.00004799458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002716871,"about_ca_topic_score_gemma":0.00006960344,"domain_scores_codex":[0.9983231,0.0001152081,0.000222403,0.0005970369,0.0003198145,0.0004224837],"domain_scores_gemma":[0.9991631,0.0002255271,0.0000416432,0.0004419381,0.00005484313,0.00007298475],"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":[0.0002673816,0.001252263,0.04344295,0.00007864241,0.00008484571,0.00004824082,0.01987636,0.3596488,0.00939775,0.05575076,0.002089008,0.508063],"study_design_scores_gemma":[0.006826704,0.001013647,0.04712258,0.0000555755,0.00002825934,0.0001388871,0.005404412,0.8914319,0.02536146,0.01027705,0.0105753,0.001764173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05770527,0.0001438334,0.9382409,0.002049156,0.0001322479,0.001402375,0.00001420329,0.000205804,0.000106187],"genre_scores_gemma":[0.7223693,0.00000687167,0.2749535,0.0003563056,0.00004654254,0.001493197,0.00003164227,0.00002085828,0.0007217455],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.664664,"threshold_uncertainty_score":0.6098549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02534179134285195,"score_gpt":0.2986221657301,"score_spread":0.2732803743872481,"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."}}