{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003518629,0.001470066,0.0007869536,0.0004597249,0.0004187719,0.0009845903,0.001096756,0.001258415,0.002024251],"category_scores_gemma":[0.009951281,0.0003775021,0.0004851681,0.0003625303,0.001170935,0.001778138,0.002127428,0.00267568,0.0007941179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007289217,"about_ca_system_score_gemma":0.0006925153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001276059,"about_ca_topic_score_gemma":0.002299284,"domain_scores_codex":[0.9987139,0.0005895983,0.00005495867,0.0002726851,0.0002494208,0.0001195092],"domain_scores_gemma":[0.9966877,0.002091517,0.0002056392,0.000658861,0.0002512468,0.000104953],"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":[0.0002859656,0.000127267,0.003636241,0.0001762865,0.00009219685,0.0001311389,0.0001426915,0.8570548,0.01741131,0.02313525,0.003789947,0.09401696],"study_design_scores_gemma":[0.00001315783,0.00006359243,0.000259451,0.00001820448,0.00001114739,0.00005914998,0.00001195218,0.986634,0.00495051,0.006594511,0.001376105,0.000008097687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09673103,0.001402277,0.8897685,0.0009045079,0.0001499449,0.00006995464,0.0001517943,0.002294293,0.00852759],"genre_scores_gemma":[0.8839696,0.0004962726,0.110829,0.0004901137,0.00008483477,0.00009127588,0.0003140804,0.0002843874,0.003440464],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003518629,"threshold_uncertainty_score":0.01860851,"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."}}