{"id":"W3133289359","doi":"10.1016/j.neucom.2020.09.091","title":"Domain generalization via optimal transport with metric similarity learning","year":2021,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; Western University; Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Leverage (statistics); Artificial intelligence; Computer science; Similarity (geometry); Generalization; Invariant (physics); Machine learning; Domain (mathematical analysis); Pattern recognition (psychology); Metric (unit); Boundary (topology); Mathematics; Image (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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003738099,0.0001817396,0.0001987301,0.0001676225,0.000432507,0.0001950084,0.0003490912,0.00005932655,0.00002485318],"category_scores_gemma":[0.00004230907,0.000182478,0.0000715486,0.001634439,0.00002620358,0.0003646527,0.0001164842,0.0004052837,0.00001728231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003262361,"about_ca_system_score_gemma":0.0001001343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008169683,"about_ca_topic_score_gemma":0.000004280038,"domain_scores_codex":[0.9980473,0.0002581714,0.0002903861,0.0005928876,0.0004374357,0.0003738462],"domain_scores_gemma":[0.9991377,0.0001283994,0.0001555985,0.0002815454,0.0001718648,0.0001248956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001149592,0.00007446605,0.02357802,0.00003472198,0.00002734875,0.0005321042,0.001863856,0.9027955,0.005358089,0.01139615,0.00001753098,0.05431071],"study_design_scores_gemma":[0.0008403242,0.0001277561,0.04422297,0.00003651689,0.00001323476,0.000268178,0.0001126453,0.9336227,0.002288854,0.0001698631,0.01790873,0.0003882392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.172336,0.00005404801,0.8249157,0.0002533198,0.0001424778,0.00008133758,1.591097e-7,0.0003320163,0.001884913],"genre_scores_gemma":[0.7035722,0.000004467181,0.2956721,0.0004772071,0.00008006507,0.000002778964,0.000009032145,0.00001901471,0.0001632034],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5312362,"threshold_uncertainty_score":0.7441236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01166318286433433,"score_gpt":0.2247388399529125,"score_spread":0.2130756570885782,"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."}}