{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001429864,0.002552032,0.001921216,0.0007963182,0.0007289578,0.002220051,0.003555883,0.002548168,0.02107346],"category_scores_gemma":[0.002451693,0.0007691288,0.00169938,0.0008272618,0.0009823126,0.00283388,0.001800588,0.002972612,0.00589927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001292766,"about_ca_system_score_gemma":0.002110727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007794928,"about_ca_topic_score_gemma":0.01200886,"domain_scores_codex":[0.9994015,0.0001444013,0.00002307089,0.0001671357,0.0001715833,0.00009228603],"domain_scores_gemma":[0.9993673,0.0002371271,0.00003180427,0.0001481186,0.0001405321,0.00007514538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006475304,0.00062651,0.001472153,0.0006071255,0.0004966029,0.000225498,0.000225626,0.3664858,0.01747134,0.01682333,0.05013036,0.5447881],"study_design_scores_gemma":[0.0001620625,0.0002266812,0.0002243182,0.00004878944,0.00005611384,0.00007264129,0.00004382613,0.9703366,0.004495789,0.008695127,0.01560669,0.00003147161],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06083651,0.005345101,0.8815525,0.001435068,0.0008433245,0.0003106048,0.0008940984,0.02835186,0.02043097],"genre_scores_gemma":[0.2876618,0.001607621,0.681272,0.00130368,0.0003643787,0.0004456683,0.003750272,0.006612172,0.01698231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02107346,"threshold_uncertainty_score":0.07049775,"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."}}