{"id":"W3011675874","doi":"10.1109/tsp.2020.2979601","title":"Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space With Softplus Loss","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; MNIST database; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Convergence (economics); Generative grammar; Generative adversarial network; Sample (material); Density ratio; Algorithm; Deep learning; Telecommunications; 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":[0.002044886,0.001150965,0.0009878653,0.0005185283,0.000229236,0.0006250326,0.001575932,0.000915033,0.001489599],"category_scores_gemma":[0.004590468,0.0004685884,0.0006963325,0.0004117753,0.001084492,0.001630411,0.001536792,0.001919314,0.0004517665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000993759,"about_ca_system_score_gemma":0.0006114184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002065111,"about_ca_topic_score_gemma":0.002206072,"domain_scores_codex":[0.9992521,0.0003197756,0.00002544839,0.0001529798,0.0001892632,0.00006033848],"domain_scores_gemma":[0.9986407,0.0008519079,0.0001284691,0.0002025411,0.0001150938,0.00006128366],"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":[0.0001540689,0.00006334943,0.0009267617,0.0000694405,0.00006332502,0.0001064265,0.00006364099,0.8711038,0.005000263,0.03138394,0.002615251,0.08844968],"study_design_scores_gemma":[0.000004953703,0.00001547562,0.00006910207,0.000003336913,0.000003793538,0.00002402598,0.00000192132,0.994276,0.000841703,0.004517817,0.0002380651,0.000003753112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01163313,0.0002425168,0.986257,0.0001597329,0.00002233987,0.00003683106,0.00004403886,0.0006697074,0.0009345817],"genre_scores_gemma":[0.7571484,0.0004327743,0.2366768,0.0005311134,0.00009712422,0.0002089501,0.0003782867,0.0003197899,0.004206727],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002065111,"threshold_uncertainty_score":0.01081455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01689495322428257,"score_gpt":0.2284269665349876,"score_spread":0.211532013310705,"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."}}