{"id":"W3139279841","doi":"10.1016/b978-0-32-395674-1.00014-7","title":"Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization","year":2021,"lang":"en","type":"preprint","venue":"Elsevier eBooks","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Segmentation; Computer science; Artificial intelligence; Mutual information; Feature learning; Pattern recognition (psychology); Scale-space segmentation; Segmentation-based object categorization; Cluster analysis; Image segmentation; Encoder; Regularization (linguistics)","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":[0.0001469528,0.0002911938,0.0002525559,0.00006210279,0.0002108176,0.0005966551,0.0004330168,0.0001594442,0.000002686962],"category_scores_gemma":[0.00002180087,0.0002853024,0.00004725057,0.0001948683,0.0001139487,0.001031305,0.0009956734,0.0003237274,0.000008370608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001918201,"about_ca_system_score_gemma":0.0001919649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001747245,"about_ca_topic_score_gemma":0.00002363867,"domain_scores_codex":[0.9983185,0.0000922273,0.0004215006,0.0005337516,0.0003732735,0.0002607393],"domain_scores_gemma":[0.9985635,0.00004548829,0.0003313485,0.0006768134,0.0002672078,0.0001156592],"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":[0.000007106568,0.000007771314,0.00007702661,0.00009189764,0.00001910882,0.000005289557,0.0007656086,0.002469956,0.0002004992,0.0006490302,0.00001296036,0.9956937],"study_design_scores_gemma":[0.001537001,0.0001316791,0.002276634,0.0008551063,0.0001293147,0.0002335472,0.0005865407,0.9682766,0.00443454,0.01160232,0.00858024,0.001356447],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007195194,0.0001307819,0.9738767,0.0002772551,0.0001484295,0.0008301,0.00001504604,0.0002463377,0.01728012],"genre_scores_gemma":[0.137126,0.00006206958,0.859056,0.001105326,0.0001732121,0.0004582049,0.0006520771,0.00003250236,0.001334614],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9943373,"threshold_uncertainty_score":0.9999599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008836309312299308,"score_gpt":0.2416323098909784,"score_spread":0.2327960005786791,"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."}}