{"id":"W3169317873","doi":"10.48550/arxiv.2106.03632","title":"Quantifying and Improving Transferability in Domain Generalization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transferability; Computer science; Classifier (UML); Generalization; Benchmark (surveying); Invariant (physics); Artificial intelligence; Machine learning; Domain (mathematical analysis); Algorithm; Transfer of learning; Theoretical computer science; 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":[0.006372664,0.001612458,0.001846861,0.00162823,0.001040276,0.001897584,0.002923212,0.002553222,0.001742954],"category_scores_gemma":[0.0264695,0.0006018448,0.001888219,0.001401885,0.002701179,0.006744658,0.006653125,0.004676732,0.0008742631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002280808,"about_ca_system_score_gemma":0.001622122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00272376,"about_ca_topic_score_gemma":0.002248371,"domain_scores_codex":[0.9963995,0.001200044,0.0002473895,0.001249316,0.0006569431,0.0002467686],"domain_scores_gemma":[0.9871029,0.006283153,0.0009359843,0.004269836,0.0009164492,0.000491672],"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":[0.0004178387,0.0003741962,0.01027495,0.0002793265,0.0002493825,0.0002522335,0.000467008,0.5985684,0.01074524,0.0301704,0.00615902,0.3420419],"study_design_scores_gemma":[0.00002557752,0.00009287532,0.0009949591,0.00002262902,0.00002314013,0.0001072742,0.00006984897,0.9540252,0.003827145,0.03969332,0.001098509,0.0000194338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08945668,0.0009247413,0.9033712,0.0008459046,0.00008675595,0.000113057,0.0001859195,0.002813807,0.002202008],"genre_scores_gemma":[0.7663692,0.0005302174,0.2277475,0.0007520423,0.0001319285,0.0002180808,0.001177103,0.0005699534,0.002504085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006372664,"threshold_uncertainty_score":0.03370225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09783610275853746,"score_gpt":0.2052525491074624,"score_spread":0.1074164463489249,"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."}}