{"id":"W4403791098","doi":"10.1145/3664647.3681509","title":"Improving the Training of the GANs with Limited Data via Dual Adaptive Noise Injection","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Queen's University; Queen's University Belfast; Department for the Economy","keywords":"Dual (grammatical number); Computer science; Training (meteorology); Noise (video); Training set; Noise measurement; Artificial intelligence; Noise reduction; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003527807,0.00009105316,0.00008320749,0.00002999183,0.0001627003,0.000159501,0.0007437886,0.0000235391,0.00000990288],"category_scores_gemma":[0.00003599597,0.00003953298,0.00003372142,0.0005306329,0.00008273635,0.0005843859,0.0004278278,0.0001330244,0.000003049637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001359261,"about_ca_system_score_gemma":0.000104628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002964839,"about_ca_topic_score_gemma":0.0002426072,"domain_scores_codex":[0.9991475,0.0001032079,0.0001219337,0.0003029839,0.0001839718,0.0001404407],"domain_scores_gemma":[0.9989779,0.0001835424,0.00004889296,0.0007159392,0.00005275493,0.00002099002],"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":[0.00004837145,0.00006441204,0.0001055991,0.00002850978,0.0003275419,0.00001964494,0.01342928,0.03691696,0.04516191,0.01882498,0.004181322,0.8808915],"study_design_scores_gemma":[0.00005997312,0.00008822203,0.0004199518,0.00003132614,0.00002383173,0.00001917169,0.0005547212,0.9929671,0.005233271,0.0001393074,0.0003921799,0.00007093467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00253224,0.00009070628,0.9944769,0.001130647,0.0003926649,0.0001412989,0.000005499315,0.00006217743,0.001167878],"genre_scores_gemma":[0.9797804,0.000002410357,0.01965629,0.0001523076,0.000150929,0.000004195297,0.000001450236,0.000006876538,0.0002451022],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9772482,"threshold_uncertainty_score":0.1612108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04165152879257931,"score_gpt":0.2279063891131841,"score_spread":0.1862548603206048,"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."}}