{"id":"W3111046435","doi":"10.1007/978-3-030-78191-0_40","title":"Teach Me to Segment with Mixed Supervision: Confident Students Become Masters","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Segmentation; Pixel; Computer science; Kullback–Leibler divergence; Entropy (arrow of time); Artificial intelligence; Divergence (linguistics); Market segmentation; Minification; Pattern recognition (psychology); Machine learning","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008175995,0.0006267328,0.0006465874,0.0005523329,0.0003391039,0.001831985,0.008089147,0.0001810793,0.00001000366],"category_scores_gemma":[0.00004976099,0.0005402094,0.0001089907,0.002918908,0.0002999204,0.0005743937,0.01219133,0.001080358,0.00002550782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005688652,"about_ca_system_score_gemma":0.0005272235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005938088,"about_ca_topic_score_gemma":0.0002526441,"domain_scores_codex":[0.9932806,0.0001372788,0.0006272513,0.002910456,0.002058754,0.0009856799],"domain_scores_gemma":[0.9955559,0.0003226225,0.0002322031,0.003060593,0.0003774313,0.0004512227],"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":[0.000008534842,0.00018657,0.005329154,0.00003925075,0.000020132,0.0001148224,0.00291885,0.8096345,0.0006984934,0.0001426038,0.00002331013,0.1808838],"study_design_scores_gemma":[0.001192842,0.0006498663,0.0422215,0.001501501,0.00002963228,0.0002407926,0.00001958931,0.924979,0.01894329,0.007467997,0.0003216754,0.002432367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1747136,0.0001601046,0.8184468,0.003778798,0.001657595,0.001041507,0.000002990568,0.0001923304,0.000006217998],"genre_scores_gemma":[0.5315014,0.00001298471,0.4662133,0.001979843,0.000137263,0.0001276786,0.000006822036,0.00001783364,0.000002877594],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3567878,"threshold_uncertainty_score":0.999705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01891792252319233,"score_gpt":0.2920403890676587,"score_spread":0.2731224665444664,"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."}}