{"id":"W4389990420","doi":"10.1016/j.patcog.2023.110213","title":"TFS-ViT: Token-level feature stylization for domain generalization","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Artificial Intelligence in Medicine (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Normalization (sociology); Security token; Artificial intelligence; Generalization; Convolutional neural network; Feature (linguistics); Pattern recognition (psychology); Transformer; Machine learning; Mathematics","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":[0.001137272,0.001561123,0.001699081,0.001786986,0.0007254404,0.001292995,0.003194045,0.001526564,0.01846399],"category_scores_gemma":[0.003585498,0.0007409302,0.001607288,0.001515759,0.00073459,0.002732484,0.003239221,0.002987568,0.01244542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008065738,"about_ca_system_score_gemma":0.001261851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004391371,"about_ca_topic_score_gemma":0.00773511,"domain_scores_codex":[0.9990174,0.0001625344,0.00005504331,0.0004540645,0.0001969516,0.0001140753],"domain_scores_gemma":[0.998592,0.0003347667,0.00004690743,0.0007479489,0.0002029965,0.00007540627],"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":[0.0006293655,0.0002295425,0.001038406,0.0002554568,0.0001506119,0.0002109452,0.0001083763,0.018404,0.03039385,0.009113762,0.06046551,0.8790001],"study_design_scores_gemma":[0.00008900867,0.0002119943,0.001252471,0.00004462578,0.00008275674,0.000401578,0.00009582479,0.871339,0.06149894,0.03422831,0.03067623,0.00007924178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008708102,0.0003815197,0.9162282,0.0001382921,0.0003035261,0.0001734472,0.002996262,0.06858474,0.002485831],"genre_scores_gemma":[0.1913555,0.0004263791,0.7694466,0.0004342448,0.000192448,0.0003978166,0.01824064,0.004904169,0.01460212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01846399,"threshold_uncertainty_score":0.06176823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08098606940649306,"score_gpt":0.2877504393642281,"score_spread":0.206764369957735,"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."}}