{"id":"W2967693052","doi":"10.48550/arxiv.1908.05770","title":"Discretely-constrained deep network for weakly supervised segmentation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Regularization (linguistics); Segmentation; Prior probability; Computer science; Artificial intelligence; Convolutional neural network; Benchmark (surveying); Mathematical optimization; Pattern recognition (psychology); Algorithm; Mathematics; 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":[0.000976022,0.001093524,0.0009322215,0.0005835665,0.0003567267,0.0007609969,0.001561366,0.001512552,0.002505035],"category_scores_gemma":[0.002856819,0.000628716,0.0005692819,0.0007223334,0.001057816,0.00128925,0.001428716,0.002085994,0.0007901369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001191916,"about_ca_system_score_gemma":0.001308224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00415664,"about_ca_topic_score_gemma":0.007031022,"domain_scores_codex":[0.999563,0.0001251914,0.00002061945,0.0001411889,0.0001085802,0.0000414251],"domain_scores_gemma":[0.9992872,0.0003121588,0.00009319168,0.000131593,0.0001278054,0.00004817162],"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":[0.0002202259,0.0001241499,0.0006815851,0.0001593873,0.00007877169,0.0001173277,0.0001180312,0.677203,0.01545474,0.02948335,0.006593445,0.269766],"study_design_scores_gemma":[0.00000382392,0.000008663458,0.00003950736,0.000003403421,0.000002001894,0.000009131196,0.00000218714,0.9923498,0.001103213,0.006109667,0.0003657571,0.000002868399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008581173,0.0002343432,0.988984,0.0001907084,0.00002321607,0.00002935595,0.0001079904,0.0008677089,0.0009815599],"genre_scores_gemma":[0.4220866,0.0004638183,0.5664957,0.0003663824,0.0001086184,0.0002703318,0.001218772,0.0003907135,0.008599132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00415664,"threshold_uncertainty_score":0.008647978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05774311155039706,"score_gpt":0.2103444496522476,"score_spread":0.1526013381018506,"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."}}