{"id":"W4387640435","doi":"10.1007/978-3-031-45676-3_31","title":"CCMix: Curriculum of Class-Wise Mixup for Long-Tailed Medical Image Classification","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Overfitting; Class (philosophy); Weighting; Machine learning; Artificial intelligence; Ambiguity; Contextual image classification; Matching (statistics); Source code; Variance (accounting); Code (set theory); Image (mathematics); Pattern recognition (psychology); Artificial neural network; Set (abstract data type); Statistics","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":[0.001840561,0.001441966,0.0007695327,0.001348803,0.000717447,0.002947338,0.003009468,0.001444815,0.1209873],"category_scores_gemma":[0.006047946,0.0008359816,0.001025165,0.001191107,0.000535325,0.002909144,0.003912383,0.002801378,0.08229309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001617553,"about_ca_system_score_gemma":0.002602187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001493224,"about_ca_topic_score_gemma":0.002811885,"domain_scores_codex":[0.9987324,0.0001537309,0.00007033958,0.0003658084,0.0005276435,0.0001500561],"domain_scores_gemma":[0.9965389,0.000724386,0.00009770849,0.000516301,0.001459,0.0006638698],"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":[0.000127796,0.000244388,0.0006534578,0.00023446,0.00001128136,0.00009641947,0.0002471863,0.003121125,0.008542374,0.02806878,0.3636787,0.594974],"study_design_scores_gemma":[0.00006182877,0.0001772418,0.002564274,0.0003154663,0.00001874136,0.0007796439,0.0001870872,0.0566456,0.024302,0.0724244,0.8424566,0.00006718615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005906175,0.0007634388,0.8136982,0.002846915,0.001511988,0.0007296037,0.003369173,0.04239248,0.1287819],"genre_scores_gemma":[0.03098851,0.000907355,0.7529801,0.001403008,0.0007840426,0.0007897154,0.008509217,0.01014462,0.1934936],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1209873,"threshold_uncertainty_score":0.4047427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03529996785640006,"score_gpt":0.3317855149365774,"score_spread":0.2964855470801774,"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."}}