{"id":"W3117983049","doi":"10.1109/vcip49819.2020.9301851","title":"GRNet: Deep Convolutional Neural Networks based on Graph Reasoning for Semantic Segmentation","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Research and Development; Fundamental Research Funds for the Central Universities","keywords":"Computer science; Artificial intelligence; Graph; Convolutional neural network; Segmentation; Deep learning; Benchmark (surveying); Feature (linguistics); Pattern recognition (psychology); Machine learning; Theoretical computer science","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":[0.0003786782,0.001752597,0.0007276929,0.001308061,0.0004244464,0.000989106,0.002276862,0.001296627,0.003689134],"category_scores_gemma":[0.0008087087,0.0006099002,0.001171725,0.001345917,0.0007367756,0.002431056,0.001031533,0.001634857,0.001877709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001371397,"about_ca_system_score_gemma":0.001146701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01315079,"about_ca_topic_score_gemma":0.02287505,"domain_scores_codex":[0.999731,0.00002544877,0.00001021856,0.0001289373,0.00006221551,0.00004211302],"domain_scores_gemma":[0.9998325,0.00003793669,0.00002596863,0.00005021382,0.00003533344,0.0000180983],"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":[0.0003051554,0.0002425236,0.001471628,0.0003740735,0.0003318333,0.0003388671,0.0001433878,0.3365546,0.04412872,0.04184911,0.02511006,0.5491502],"study_design_scores_gemma":[0.0000135855,0.00004545799,0.0003851663,0.00002230933,0.00004170771,0.00006987566,0.00001706814,0.9541932,0.01107843,0.02782768,0.006288462,0.00001707625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01873483,0.001126635,0.9594054,0.0003295178,0.0001417253,0.0001058242,0.001279228,0.01427458,0.004602247],"genre_scores_gemma":[0.3146444,0.001145351,0.6655265,0.0006805884,0.00008265281,0.0001576558,0.008146832,0.001069182,0.008546881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01315079,"threshold_uncertainty_score":0.0261485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01791314152433534,"score_gpt":0.2468122968838282,"score_spread":0.2288991553594929,"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."}}