{"id":"W3042302007","doi":"10.1016/j.neunet.2020.07.011","title":"Discretely-constrained deep network for weakly supervised segmentation","year":2020,"lang":"en","type":"article","venue":"Neural Networks","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Hôpital Notre-Dame","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Prior probability; Regularization (linguistics); Segmentation; Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Image segmentation; Mathematical optimization; Mathematics; Algorithm; Bayesian probability","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007649285,0.001048496,0.001628174,0.0007490808,0.000496974,0.001392747,0.002410988,0.002439719,0.005295828],"category_scores_gemma":[0.002456791,0.0008982705,0.0009046686,0.001198825,0.001001082,0.001735506,0.002172946,0.002671781,0.00165641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001372829,"about_ca_system_score_gemma":0.001840065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0089236,"about_ca_topic_score_gemma":0.01521688,"domain_scores_codex":[0.999537,0.00007699038,0.00002430327,0.000188307,0.00009722717,0.0000761634],"domain_scores_gemma":[0.9991799,0.000356346,0.00008111445,0.0001560407,0.0001508357,0.00007579743],"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":[0.0005972828,0.0002166939,0.0009648594,0.0002450787,0.0001185515,0.000143094,0.0001206374,0.4503447,0.02680605,0.02752932,0.01073169,0.4821819],"study_design_scores_gemma":[0.000004381929,0.00001130864,0.00006634735,0.000005563933,0.000003651503,0.00001035971,0.00000380214,0.992762,0.001484171,0.005247172,0.0003973068,0.000003878614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01194045,0.0004032168,0.9839832,0.000250848,0.00005244817,0.00003951625,0.0003426573,0.001577913,0.001409826],"genre_scores_gemma":[0.4867768,0.000657101,0.4903589,0.0005627071,0.0002053616,0.0002567912,0.003237249,0.0008264218,0.01711859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0089236,"threshold_uncertainty_score":0.01774329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02421797583367849,"score_gpt":0.2605757926334563,"score_spread":0.2363578167997778,"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."}}