{"id":"W3089984691","doi":"10.1109/ijcnn52387.2021.9533449","title":"Assisting the Adversary to Improve GAN Training","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Discriminator; Adversary; Regularization (linguistics); Computer science; Generator (circuit theory); Norm (philosophy); Stability (learning theory); Algorithm; Perspective (graphical); Artificial intelligence; Machine learning; Computer security; Telecommunications; Power (physics); Physics","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":[0.0006701687,0.0002994234,0.00034427,0.00006369715,0.0002957231,0.001033336,0.001766541,0.0001428918,0.00007346904],"category_scores_gemma":[0.0002900757,0.0002079547,0.0002348512,0.0002922732,0.00003600953,0.0002216014,0.002742678,0.0005569336,0.00002514328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006238546,"about_ca_system_score_gemma":0.000345633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001977302,"about_ca_topic_score_gemma":0.000083281,"domain_scores_codex":[0.9977716,0.0002204247,0.0003232959,0.0009279056,0.0003297326,0.0004270523],"domain_scores_gemma":[0.9979439,0.0002687647,0.0001427079,0.001311156,0.0001849781,0.0001484882],"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":[0.000005418395,0.00005634584,0.00005323727,0.00004931308,0.000288577,0.00009248788,0.0120908,0.120122,0.006818712,0.00330689,0.009481855,0.8476344],"study_design_scores_gemma":[0.0002438387,0.00007785238,0.001955538,0.0002983453,0.0000718139,0.00001641386,0.002645292,0.964627,0.01555987,0.002020083,0.01128287,0.001201037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007729751,0.0001598501,0.9616755,0.006527766,0.002640492,0.0003073067,0.00000349409,0.0001481011,0.0277645],"genre_scores_gemma":[0.758734,0.00001005995,0.2366847,0.002611952,0.0007403354,0.00005316439,0.00000569215,0.00001733873,0.001142657],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8464333,"threshold_uncertainty_score":0.9964482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03495936617294925,"score_gpt":0.2539614238375831,"score_spread":0.2190020576646338,"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."}}