{"id":"W3176239531","doi":"10.48550/arxiv.2103.04813","title":"Boosting Semi-supervised Image Segmentation with Global and Local Mutual\\n Information Regularization","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Feature learning; Pattern recognition (psychology); Mutual information; Scale-space segmentation; Cluster analysis; Segmentation-based object categorization; Encoder; Image segmentation; Boosting (machine learning); Regularization (linguistics)","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":[],"consensus_categories":[],"category_scores_codex":[0.00004475287,0.00009455559,0.00007421857,0.00003473786,0.0001835545,0.00009332394,0.0001764649,0.00003819865,0.000004980469],"category_scores_gemma":[0.00001269717,0.0001047401,0.00001695624,0.0009757705,0.00006627916,0.002339364,0.0001544096,0.00006251237,0.00002037964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001050177,"about_ca_system_score_gemma":0.0000540801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006280384,"about_ca_topic_score_gemma":0.00001585184,"domain_scores_codex":[0.999366,0.00003998495,0.0001010501,0.0002822023,0.00006484788,0.0001458825],"domain_scores_gemma":[0.999364,0.00003667724,0.00008420488,0.0002772766,0.0001625243,0.00007538362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006360561,0.00007364295,0.00863851,0.00005355908,0.00004318367,0.000146925,0.0006217811,0.2516905,0.003028867,0.6652345,0.0002226806,0.07018221],"study_design_scores_gemma":[0.0006274461,0.00003362715,0.002374111,0.0000166699,0.00001628183,0.00003804153,0.0002860208,0.9853025,0.002182423,0.008741425,0.0002217207,0.0001597456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0791676,0.00001022342,0.9192283,0.000164088,0.00002456462,0.0001183254,0.000003559083,0.0001227421,0.001160577],"genre_scores_gemma":[0.9495751,0.00002444968,0.05000142,0.0002205888,0.00001237564,8.941239e-7,0.00004038526,0.000003486813,0.0001213321],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8704075,"threshold_uncertainty_score":0.4271177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02023456466147201,"score_gpt":0.1749603495150645,"score_spread":0.1547257848535925,"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."}}