{"id":"W2972781556","doi":"10.1109/icarm.2019.8833973","title":"Semantic Segmentation via Structured Refined Prediction and Dual Global Priors","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Prior probability; Convolution (computer science); Context (archaeology); Residual; Transformation (genetics); Convolutional neural network; Boundary (topology); Scale (ratio); Set (abstract data type); Computer vision; Pattern recognition (psychology); Algorithm; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003796003,0.00007953747,0.00006997471,0.00002054671,0.00006262867,0.00004735386,0.0001312825,0.00003330429,0.0000158225],"category_scores_gemma":[0.00000313726,0.00007014138,0.00001373827,0.0002724057,0.00001622172,0.0004151872,0.0001023978,0.00003414437,0.00004105315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004196959,"about_ca_system_score_gemma":0.00001116241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007267749,"about_ca_topic_score_gemma":0.00002170392,"domain_scores_codex":[0.9992927,0.00001740446,0.0001285385,0.0002930688,0.0001403779,0.0001279112],"domain_scores_gemma":[0.9995747,0.00002135303,0.00005368655,0.0002719475,0.00002821619,0.00005008605],"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":[0.0000493793,0.00009726042,0.0988918,0.00006780942,0.00006596887,0.000007132361,0.0006155105,0.01022376,0.1596076,0.3017959,0.002612776,0.4259651],"study_design_scores_gemma":[0.001277397,0.0002334768,0.3354494,0.00001395,0.00001787314,0.0001087898,0.00006220139,0.6074577,0.00853639,0.04518548,0.001290034,0.0003673522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3635641,0.00001620772,0.6348282,0.0005003473,0.0001688527,0.0002686224,0.000002535685,0.0001914863,0.000459587],"genre_scores_gemma":[0.9225965,0.000006811024,0.07692457,0.0002288412,0.00003200395,0.00001123392,0.000008667497,0.00000342171,0.0001879867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.597234,"threshold_uncertainty_score":0.2860282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00670501018979337,"score_gpt":0.2423606356839914,"score_spread":0.235655625494198,"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."}}