{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001070612,0.000295272,0.0002916294,0.00002574288,0.0003693587,0.0001761999,0.0009836678,0.0001121472,0.00002310917],"category_scores_gemma":[0.00003807591,0.0002838674,0.0001735346,0.0008772989,0.0000775899,0.0006328782,0.0002239877,0.0002811179,0.000017103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003277813,"about_ca_system_score_gemma":0.00001976719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001739937,"about_ca_topic_score_gemma":0.000008797771,"domain_scores_codex":[0.9977989,0.00007967823,0.000432495,0.0007541804,0.0002234948,0.0007112685],"domain_scores_gemma":[0.998516,0.0004050677,0.0001689775,0.0004830765,0.0000877859,0.0003390987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006207472,0.00002146166,0.0003289786,0.00001392697,0.00002453622,0.00000643653,0.0001677199,0.8155573,0.0008209625,0.02258942,0.007908404,0.1524988],"study_design_scores_gemma":[0.0005918274,0.000176273,0.0003035971,0.000006950751,0.00001666794,0.000007932275,0.00001645007,0.9923735,0.0001592912,0.00286476,0.003175089,0.0003077085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002441062,0.0003320036,0.9846426,0.01011522,0.0004620395,0.001150077,0.000007337345,0.0006040407,0.0002456694],"genre_scores_gemma":[0.7712536,0.00004348351,0.2171565,0.009187329,0.001794846,0.0003725977,0.0001067128,0.00004486501,0.00004003317],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7688125,"threshold_uncertainty_score":0.9999614,"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."}}