{"id":"W4385834296","doi":"10.1109/access.2023.3305385","title":"RandMixAugment: A Novel Unified Technique for Region- and Image-Level Data Augmentations","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Korea Agency for Infrastructure Technology Advancement; Ministry of Land, Infrastructure and Transport","keywords":"Computer science; Generalization; Artificial intelligence; Deep learning; Image (mathematics); Masking (illustration); Machine learning; Data modeling; Contextual image classification; Pattern recognition (psychology); Mathematics; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0001830838,0.0001157603,0.0001167927,0.0001236349,0.0002758112,0.0002374205,0.002014225,0.00003951064,0.000001151727],"category_scores_gemma":[0.00004297114,0.0001140849,0.00002159722,0.0009478524,0.00006086188,0.001593264,0.0007392116,0.0000784289,0.00001052429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001909953,"about_ca_system_score_gemma":0.0000393944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001317569,"about_ca_topic_score_gemma":0.00001572511,"domain_scores_codex":[0.998875,0.00001524713,0.0001947113,0.0005452817,0.000126808,0.0002430019],"domain_scores_gemma":[0.9982925,0.0003208593,0.0000966059,0.001140641,0.00007460643,0.0000747717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001044799,0.0004067367,0.0005240862,0.0002735298,0.0001472399,0.00004284808,0.0006633358,0.003199253,0.3478482,0.1979454,0.3330209,0.115824],"study_design_scores_gemma":[0.00610922,0.0001419917,0.008180789,0.0001700153,0.00009750755,0.0001768688,0.00007023869,0.5648285,0.1496916,0.2124156,0.05651736,0.001600353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006588806,0.00001769565,0.9936206,0.003873712,0.0001573532,0.001088779,0.0001149925,0.0003390838,0.0001288737],"genre_scores_gemma":[0.3364382,0.0002973559,0.6563261,0.00151555,0.0003080922,0.003540306,0.0003710453,0.00005965466,0.001143766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5616292,"threshold_uncertainty_score":0.4652246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2366283297808449,"score_gpt":0.4054351063097579,"score_spread":0.1688067765289129,"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."}}