{"id":"W3199813582","doi":"10.2139/ssrn.4188684","title":"Hcdg: A Hierarchical Consistency Framework for Domain Generalization on Medical Image Segmentation","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trinity College","funders":"","keywords":"Generalization; Consistency (knowledge bases); Artificial intelligence; Segmentation; Computer science; Image segmentation; Image (mathematics); Domain (mathematical analysis); Pattern recognition (psychology); Computer vision; Mathematics","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":[0.004488598,0.001214283,0.002532627,0.002570891,0.0008531843,0.001720399,0.004681798,0.00311765,0.003246145],"category_scores_gemma":[0.007582715,0.001057262,0.001981966,0.002254545,0.001483614,0.0025286,0.004686204,0.00392336,0.001293263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001224382,"about_ca_system_score_gemma":0.002191909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009726207,"about_ca_topic_score_gemma":0.01114848,"domain_scores_codex":[0.998165,0.0005950474,0.00009550185,0.0005976721,0.0003993952,0.0001473381],"domain_scores_gemma":[0.9970384,0.001192937,0.0001743295,0.0009200063,0.0005081857,0.000166118],"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":[0.0003710066,0.0002637909,0.001538408,0.0003804856,0.0003333154,0.0001810172,0.0002317575,0.301069,0.01372783,0.03083959,0.01733133,0.6337326],"study_design_scores_gemma":[0.00001745399,0.00004101643,0.0002609968,0.00001648851,0.00001975031,0.00005201604,0.00001768876,0.9750182,0.002483569,0.02025665,0.001802524,0.00001377788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00186869,0.0001730815,0.9959805,0.0000795838,0.00002120609,0.00005037361,0.0001296961,0.001496714,0.0002001868],"genre_scores_gemma":[0.1129898,0.0003710421,0.8808723,0.0004587299,0.0001497891,0.0002660181,0.001823196,0.001060617,0.002008516],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009726207,"threshold_uncertainty_score":0.02373827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01189869361805534,"score_gpt":0.2811937815157058,"score_spread":0.2692950878976505,"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."}}