{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001346771,0.0002677714,0.0003103623,0.0003354537,0.0007329788,0.0006206301,0.0003428454,0.0001126174,0.0003878837],"category_scores_gemma":[0.0003632705,0.000276873,0.0002566286,0.0005994971,0.00003880919,0.0008018684,0.0001631263,0.0004466421,0.001067455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000885827,"about_ca_system_score_gemma":0.00004693239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001516819,"about_ca_topic_score_gemma":0.00001444526,"domain_scores_codex":[0.9974606,0.0003560894,0.0004603285,0.000658365,0.0005053254,0.0005592761],"domain_scores_gemma":[0.9983974,0.0007169369,0.0003203618,0.0002196795,0.0002097507,0.0001359343],"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":[0.0002391651,0.0001169239,0.009572983,0.000302185,0.001215879,0.0001279376,0.01026966,0.03643878,0.009304982,0.0003801147,0.0007652585,0.9312661],"study_design_scores_gemma":[0.007852215,0.0009829537,0.006578508,0.0001330764,0.0003992321,0.00004005193,0.004222534,0.9521928,0.004953954,0.004859736,0.01643401,0.001350897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09165891,0.00005239969,0.904079,0.0006094968,0.0009926083,0.0004394529,0.000009677289,0.0008515341,0.001306958],"genre_scores_gemma":[0.9603816,0.00003171789,0.03547764,0.0002920871,0.000291721,0.0004912266,0.0005647653,0.00006644747,0.002402823],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9299152,"threshold_uncertainty_score":0.9999683,"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."}}