{"id":"W4388336668","doi":"10.1016/j.patcog.2023.110091","title":"Learning a target-dependent classifier for cross-domain semantic segmentation: Fine-tuning versus meta-learning","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Classifier (UML); Computer science; Artificial intelligence; Domain adaptation; Segmentation; Initialization; Exploit; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002650879,0.001784017,0.00288308,0.001489615,0.000667268,0.001932283,0.00352331,0.003467893,0.001971273],"category_scores_gemma":[0.005397098,0.0007414596,0.00182231,0.001425085,0.001087242,0.003269096,0.002341983,0.00375373,0.001598698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00109748,"about_ca_system_score_gemma":0.001587126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00429547,"about_ca_topic_score_gemma":0.00560872,"domain_scores_codex":[0.9986075,0.0002683616,0.00007880476,0.0007275697,0.0001416032,0.0001761869],"domain_scores_gemma":[0.9975314,0.001182597,0.0001327879,0.0005276321,0.0004393204,0.0001862102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007151602,0.0007639174,0.003310524,0.0002935378,0.0004839288,0.0001470438,0.0001795485,0.1397942,0.044821,0.003391499,0.008023106,0.7980765],"study_design_scores_gemma":[0.00001447935,0.00006787787,0.000424746,0.00001466796,0.0000483678,0.00005174268,0.00003734741,0.9862376,0.006847481,0.005757014,0.0004845204,0.00001402191],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04366653,0.0008761519,0.9496434,0.0003333436,0.0001343174,0.0000901393,0.0001706428,0.003932015,0.001153443],"genre_scores_gemma":[0.6765733,0.0004888396,0.3157669,0.0008372122,0.000170541,0.0002041934,0.00148238,0.0008153434,0.003661378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00429547,"threshold_uncertainty_score":0.01401931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1162820487623151,"score_gpt":0.3277321265819838,"score_spread":0.2114500778196686,"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."}}