{"id":"W2741237521","doi":"10.24963/ijcai.2017/479","title":"Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Parsing; Residual; Computer science; Boundary (topology); Artificial intelligence; Convolutional neural network; Object (grammar); Cascade; Iterative refinement; Machine learning; Data mining; Pattern recognition (psychology); Algorithm; 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":[0.001102994,0.001506022,0.0007017697,0.001035221,0.0005490876,0.0006531986,0.002523416,0.001405322,0.00376159],"category_scores_gemma":[0.002909275,0.0006192196,0.000891441,0.0008364123,0.0006664869,0.002416129,0.001435497,0.002106516,0.00160737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008223939,"about_ca_system_score_gemma":0.00134487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01255248,"about_ca_topic_score_gemma":0.02537812,"domain_scores_codex":[0.9993987,0.00008366795,0.0000236042,0.0003000877,0.0001200262,0.0000739683],"domain_scores_gemma":[0.9993461,0.0001654028,0.00007388896,0.0001713104,0.0002052634,0.00003806584],"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":[0.0002776235,0.0001558633,0.002427925,0.0001565481,0.00008680129,0.0001989666,0.0002527983,0.2771496,0.03069088,0.01072078,0.01359694,0.6642852],"study_design_scores_gemma":[0.00001228732,0.00003048555,0.0005998577,0.00001368268,0.00002753867,0.00003795435,0.00002810178,0.9830127,0.009041995,0.004883639,0.00229484,0.0000168518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04038833,0.000648517,0.9461803,0.0003117484,0.00009737232,0.00008279295,0.0004543259,0.008347913,0.003488703],"genre_scores_gemma":[0.3893286,0.0003904041,0.5973327,0.0004208573,0.00007333414,0.0001470246,0.002639455,0.0009522802,0.008715507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01255248,"threshold_uncertainty_score":0.02495879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02698253593375954,"score_gpt":0.3218867824328213,"score_spread":0.2949042464990617,"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."}}