{"id":"W3094327244","doi":"","title":"Mutual information deep regularization for semi-supervised segmentation","year":2020,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Artificial intelligence; Segmentation; Regularization (linguistics); Computer science; Mutual information; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001230349,0.0001145688,0.0001042803,0.00007792285,0.0001457211,0.0002230301,0.0002516139,0.0000819563,0.00004272121],"category_scores_gemma":[0.0001203819,0.0001124548,0.00005326605,0.0003239831,0.00001204469,0.002359236,0.00007663044,0.00006772699,0.0003173249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003091059,"about_ca_system_score_gemma":0.0000375596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002823353,"about_ca_topic_score_gemma":0.000002701751,"domain_scores_codex":[0.9991114,0.00004212972,0.0002104999,0.0002082071,0.0002496079,0.0001781501],"domain_scores_gemma":[0.9994054,0.00005102325,0.0001148837,0.0001778914,0.000141059,0.0001097811],"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":[0.0004526665,0.0001661912,0.0007514275,0.000503168,0.00008692472,0.000005452936,0.07267016,0.01074604,0.1744237,0.02651285,0.1064537,0.6072277],"study_design_scores_gemma":[0.001318648,0.0001692181,0.0002912982,0.0000310929,0.00001255171,0.000002467127,0.0008358553,0.9054871,0.0659422,0.0009057901,0.0247536,0.0002502102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01190166,0.00001803259,0.9784562,0.008048429,0.0002486955,0.0004667591,0.00000891419,0.0002207017,0.0006305805],"genre_scores_gemma":[0.7665902,0.00004651632,0.2190764,0.01201462,0.0004050261,0.000279226,0.0009236466,0.00003070867,0.000633652],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8947411,"threshold_uncertainty_score":0.4585773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01474416950835117,"score_gpt":0.2350154427099159,"score_spread":0.2202712732015648,"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."}}