{"id":"W4323817659","doi":"10.1101/2023.03.08.531734","title":"Class-imbalanced Unsupervised and Semi-Supervised Domain Adaptation for Histopathology Images","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Waterloo","funders":"","keywords":"Computer science; Leverage (statistics); Domain adaptation; Artificial intelligence; Transfer of learning; Labeled data; Domain (mathematical analysis); Machine learning; Adaptation (eye); Pattern recognition (psychology); Class (philosophy); Supervised learning; Classifier (UML); Mathematics; Artificial neural network","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"],"consensus_categories":[],"category_scores_codex":[0.001643578,0.0006112214,0.000706496,0.0004902232,0.0003635974,0.0005683926,0.001116533,0.0005651217,0.000008421793],"category_scores_gemma":[0.0005389583,0.0006970541,0.000188878,0.0006048408,0.0001698087,0.0004287812,0.0007859519,0.0006920309,0.00006263685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002472322,"about_ca_system_score_gemma":0.0005119371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002525779,"about_ca_topic_score_gemma":0.000003902172,"domain_scores_codex":[0.99608,0.0003939059,0.0006933527,0.001651445,0.0004387231,0.0007425419],"domain_scores_gemma":[0.9968874,0.0004287065,0.0004552701,0.001369708,0.0005391165,0.0003198189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001746576,0.0002111384,0.004513849,0.001291057,0.0001909379,0.0002249049,0.000794473,0.002865051,0.9541358,0.03373438,0.001723972,0.0001398311],"study_design_scores_gemma":[0.007409463,0.0005090775,0.4048432,0.00100362,0.0002328165,4.065714e-7,0.0001618921,0.5097928,0.03027134,0.0008329277,0.04046378,0.004478693],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1327657,0.0009011559,0.8587998,0.001994791,0.002258584,0.00138233,0.0001473415,0.00172652,0.00002375881],"genre_scores_gemma":[0.7722582,0.0002548132,0.2257353,0.0006223848,0.0003002648,0.0006226983,0.000002212122,0.0001488872,0.00005522864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9238644,"threshold_uncertainty_score":0.9995481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02710945160522733,"score_gpt":0.2364663121081186,"score_spread":0.2093568605028913,"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."}}