{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003147517,0.0001125989,0.0001128007,0.00002967774,0.001946005,0.0006998675,0.0005841235,0.0000576403,0.000006076408],"category_scores_gemma":[0.00009587112,0.0001071904,0.00003229448,0.00008049729,0.0001208314,0.0003161785,0.0003770711,0.000104788,0.000004145602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007763218,"about_ca_system_score_gemma":0.00005135885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001179554,"about_ca_topic_score_gemma":0.0002726228,"domain_scores_codex":[0.999004,0.00002651712,0.0001747179,0.0004088469,0.0001276686,0.0002582686],"domain_scores_gemma":[0.9987628,0.00009279582,0.0001220428,0.0008438514,0.00007162957,0.0001069069],"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":[0.00001272048,0.00007513505,0.03176641,0.00002396156,0.0000423925,0.000001417211,0.0001203548,0.03069766,0.00003946369,0.07178075,0.004392094,0.8610476],"study_design_scores_gemma":[0.0003078844,0.00004288257,0.1696794,0.00002235533,0.00001024375,0.00001004081,0.00001139414,0.8215289,0.00001801011,0.002599072,0.005658024,0.0001117889],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00680629,0.0001210712,0.9813042,0.006438383,0.0002657342,0.0003080278,0.000004852739,0.000254438,0.004497022],"genre_scores_gemma":[0.782725,0.00001413367,0.2167355,0.0001846537,0.0001245808,0.00007796542,0.000004184128,0.000006290996,0.0001277269],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8609359,"threshold_uncertainty_score":0.9993533,"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."}}