{"id":"W4403067046","doi":"10.1007/978-3-031-72114-4_50","title":"Progressively Correcting Soft Labels via Teacher Team for Knowledge Distillation in Medical Image Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Distillation; Segmentation; Image segmentation; Artificial intelligence; Computer vision; Image (mathematics); Soft computing; Artificial neural network; Chromatography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001713968,0.00158399,0.00218546,0.001243336,0.0009980501,0.001905283,0.003514004,0.003206867,0.005955389],"category_scores_gemma":[0.004861425,0.001121867,0.001508981,0.001260805,0.00133686,0.002481271,0.003693006,0.003382282,0.002479454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008525805,"about_ca_system_score_gemma":0.002114421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01069267,"about_ca_topic_score_gemma":0.01908828,"domain_scores_codex":[0.998899,0.0002648269,0.00006398813,0.0003884939,0.0002312811,0.0001524356],"domain_scores_gemma":[0.9971457,0.001669049,0.000139827,0.0004306434,0.0004969748,0.0001177967],"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":[0.0005152137,0.0001549107,0.000628669,0.00025038,0.0001284524,0.0001696293,0.0003273794,0.1479267,0.02030226,0.00714332,0.008146483,0.8143067],"study_design_scores_gemma":[0.00002118421,0.00006532262,0.0001568993,0.00002215818,0.00003521392,0.00006229801,0.00004543966,0.9785061,0.01058981,0.008941062,0.001537992,0.00001642124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01830595,0.0005842599,0.974442,0.0003060627,0.00009950397,0.00005978423,0.0001874406,0.004814716,0.001200248],"genre_scores_gemma":[0.2269352,0.000294047,0.7621295,0.0003944001,0.0001350641,0.0001402824,0.001164159,0.001038095,0.007769151],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01069267,"threshold_uncertainty_score":0.02126092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03043388949384937,"score_gpt":0.311989133413732,"score_spread":0.2815552439198826,"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."}}