{"id":"W4388947366","doi":"10.1016/j.eswa.2023.122695","title":"Scale-pyramid dynamic atrous convolution for pixel-level labeling","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Pixel; Convolutional neural network; Convolution (computer science); Kernel (algebra); Artificial intelligence; Scale (ratio); Granularity; Upsampling; Exploit; Pattern recognition (psychology); Algorithm; Image (mathematics); Artificial neural network; 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":[0.0004332043,0.0004825773,0.0005638836,0.000644593,0.0003643597,0.0008786015,0.00109721,0.0008425552,0.005028032],"category_scores_gemma":[0.001086159,0.000310324,0.0005758341,0.001115199,0.0003987141,0.0008610016,0.001084616,0.0009466062,0.002010056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008611141,"about_ca_system_score_gemma":0.00112576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007215985,"about_ca_topic_score_gemma":0.01276321,"domain_scores_codex":[0.99967,0.00003674446,0.00001595025,0.00008703092,0.0001350671,0.00005517227],"domain_scores_gemma":[0.9996819,0.00005622062,0.00002305506,0.0001207122,0.00009028719,0.0000277956],"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":[0.0002091356,0.0001318017,0.0006522597,0.0001303339,0.00006436467,0.0001030816,0.0000972061,0.06300973,0.08610965,0.02770125,0.00781869,0.8139725],"study_design_scores_gemma":[0.000007034678,0.00003208921,0.0003981105,0.000009938308,0.0000144612,0.0001289537,0.00001797424,0.9580051,0.02656279,0.009535701,0.00527611,0.00001181018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006623941,0.0001248561,0.9899301,0.00007532828,0.00002384264,0.00002711764,0.0001032329,0.001445419,0.001646095],"genre_scores_gemma":[0.223159,0.0003430021,0.7698502,0.0001793155,0.0000372765,0.00007551657,0.0006440545,0.0003165033,0.00539512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007215985,"threshold_uncertainty_score":0.01682049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03009774191278934,"score_gpt":0.2960657762361329,"score_spread":0.2659680343233435,"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."}}