{"id":"W4322753738","doi":"10.1016/j.patcog.2023.109474","title":"Fourier-based augmentation with applications to domain generalization","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":false,"ca_institutions":"Communications Research Centre Canada","funders":"National Major Science and Technology Projects of China","keywords":"Generalization; Fourier transform; Computer science; Domain (mathematical analysis); Frequency domain; Fourier series; Artificial intelligence; Fourier domain; Semantics (computer science); Algorithm; Mathematics; Computer vision; Mathematical analysis","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002374138,0.0001022696,0.00007485353,0.0002783255,0.0001837191,0.0001665617,0.0001828778,0.00003449418,0.00006062621],"category_scores_gemma":[0.00001167889,0.0001016543,0.0000264343,0.001070014,0.00001235455,0.0002901258,0.00003097808,0.00005878124,0.001540919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004850613,"about_ca_system_score_gemma":0.000034066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001516494,"about_ca_topic_score_gemma":0.00002881294,"domain_scores_codex":[0.9989507,0.00008123084,0.0001670208,0.0003188858,0.0002891869,0.0001929945],"domain_scores_gemma":[0.9994234,0.00005261404,0.00008552926,0.0002246109,0.0001157772,0.00009806817],"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":[0.00001331586,0.00004866222,0.001905335,0.00002643885,0.00001232278,0.000007070448,0.0009369421,0.006872431,0.002494995,0.0006294973,0.0008759202,0.9861771],"study_design_scores_gemma":[0.004395943,0.0006734265,0.04483471,0.0002486335,0.00004789109,0.00002535138,0.000946247,0.8575234,0.01678354,0.01670503,0.05631054,0.001505318],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03979435,0.000002594312,0.9566874,0.001759837,0.00008789109,0.000457242,0.000009246395,0.0004826408,0.0007187917],"genre_scores_gemma":[0.749764,0.000006638822,0.243101,0.004424251,0.0001778969,0.001180208,0.001055072,0.00003618138,0.0002547859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9846718,"threshold_uncertainty_score":0.9992365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04440216646547513,"score_gpt":0.2817551091962559,"score_spread":0.2373529427307808,"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."}}