{"id":"W4287597924","doi":"10.1109/tpami.2022.3228915","title":"Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Discriminator; Computer science; Generator (circuit theory); Regression; Categorical variable; Benchmark (surveying); Artificial intelligence; Scalar (mathematics); Pattern recognition (psychology); Algorithm; Machine learning; Mathematics; Statistics; Power (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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003402165,0.0002777337,0.0004142938,0.000335598,0.0008434677,0.0002109819,0.0003703525,0.00005808793,0.0003396553],"category_scores_gemma":[0.000006743738,0.0002571243,0.0001801734,0.0008972268,0.0001204692,0.0002741393,0.00003676933,0.0003865681,0.000004078009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005051232,"about_ca_system_score_gemma":0.0000375178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004234817,"about_ca_topic_score_gemma":0.0003818518,"domain_scores_codex":[0.9979982,0.0002363443,0.000379277,0.0007195509,0.0003748626,0.0002917276],"domain_scores_gemma":[0.9990241,0.0002733843,0.0001390339,0.0003164649,0.00009139656,0.0001556165],"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":[0.0000421006,0.00042302,0.0001772861,0.000004078212,0.0009513871,0.00002201097,0.000463875,0.8153574,0.000945817,0.000867094,0.000096138,0.1806498],"study_design_scores_gemma":[0.0003027114,0.000316226,0.0002402105,0.000004311556,0.0003534612,0.00003172764,0.0001169828,0.9848864,0.01237758,0.0008496242,0.0002002945,0.0003204631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001187441,0.0001506628,0.9968416,0.0009627179,0.0004167178,0.0001664156,0.0001932661,0.00005577818,0.00002541107],"genre_scores_gemma":[0.9862288,0.0001412143,0.01141838,0.001883132,0.00007002673,0.00006628549,0.00002622338,0.00001267442,0.0001532865],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9854232,"threshold_uncertainty_score":0.9999881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02525702039574126,"score_gpt":0.2677769088405544,"score_spread":0.2425198884448132,"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."}}