{"id":"W4386253585","doi":"10.1007/s10489-023-04935-4","title":"Dense-scale dynamic network with filter-varying atrous convolution for semantic segmentation","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Pixel; Convolution (computer science); Pattern recognition (psychology); Filter (signal processing); Computer vision; Convolutional neural network; Algorithm; Artificial neural network","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":[0.0001750912,0.0001909788,0.0001687651,0.00007912203,0.0003634365,0.00008288511,0.0006029689,0.00005627909,0.000004885987],"category_scores_gemma":[0.000007329034,0.0001827428,0.00004599059,0.001303019,0.00007568002,0.0002458714,0.0001513405,0.0001238887,0.0002474408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008510422,"about_ca_system_score_gemma":0.00003277763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004704517,"about_ca_topic_score_gemma":0.00003102575,"domain_scores_codex":[0.9983525,0.00001765861,0.0002887337,0.0006006212,0.0002218177,0.0005186365],"domain_scores_gemma":[0.9988124,0.0003330663,0.0001527666,0.0005442219,0.00007689562,0.00008068742],"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":[0.00007404283,0.00004816255,0.0001662271,0.00006876155,0.00003894531,0.000006571806,0.0007408653,0.674412,0.01815507,0.09211718,0.001749858,0.2124224],"study_design_scores_gemma":[0.0001721567,0.0001131393,0.0003711658,0.00003892485,0.00001932814,0.000020006,0.00008525674,0.9278266,0.01498257,0.05513634,0.0008770554,0.0003574188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009173154,0.00005166899,0.9882821,0.0003056847,0.0001692453,0.001060093,0.0000039082,0.0006534164,0.0003006613],"genre_scores_gemma":[0.7698605,0.00007230576,0.2286794,0.0002711714,0.00008796109,0.0007594258,0.00005740971,0.00002673943,0.0001851455],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7606874,"threshold_uncertainty_score":0.7452034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02220179332783397,"score_gpt":0.27622045817938,"score_spread":0.254018664851546,"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."}}