{"id":"https://openalex.org/W2945027741","doi":"https://doi.org/10.48550/arxiv.1905.10887","title":"Classification Accuracy Score for Conditional Generative Models","display_name":"Classification Accuracy Score for Conditional Generative Models","publication_year":2019,"publication_date":"2019-05-26","ids":{"openalex":"https://openalex.org/W2945027741","doi":"https://doi.org/10.48550/arxiv.1905.10887","mag":"2945027741"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1905.10887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.10887","pdf_url":"https://arxiv.org/pdf/1905.10887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.10887","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026262869","display_name":"Suman V. Ravuri","orcid":"https://orcid.org/0000-0002-7481-7633","observed_orcids":["https://orcid.org/0000-0002-7481-7633"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravuri, Suman","raw_affiliation_strings":["London , UK N1C 4AG","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"London , UK N1C 4AG","institution_ids":[]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003562101","display_name":"Oriol Vinyals","orcid":"https://orcid.org/0000-0001-7848-7283","observed_orcids":["https://orcid.org/0000-0001-7848-7283"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinyals, Oriol","raw_affiliation_strings":["London , UK N1C 4AG","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"London , UK N1C 4AG","institution_ids":[]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":179,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"12247","last_page":"12258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conditional-generative-models","display_name":"conditional generative models","score":0.9240000247955322},{"id":"https://openalex.org/keywords/generative-model-evaluation","display_name":"generative model evaluation","score":0.7910000085830688},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.7229999899864197},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.9539999961853027},{"id":"https://openalex.org/keywords/autoregressive-models","display_name":"autoregressive models","score":0.8370000123977661},{"id":"https://openalex.org/keywords/biggan","display_name":"BigGAN","score":0.8330000042915344},{"id":"https://openalex.org/keywords/inception-score","display_name":"Inception Score","score":0.7580000162124634},{"id":"https://openalex.org/keywords/frechet-inception-distance","display_name":"Fr\u00e9chet Inception Distance","score":0.8790000081062317}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675941348075867},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.64653080701828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6444071531295776},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6253985166549683},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6028041839599609},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5623112320899963},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.547588586807251},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5134668946266174},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5000214576721191},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4716094136238098},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3805815577507019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23568889498710632},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13450032472610474}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1905.10887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.10887","pdf_url":"https://arxiv.org/pdf/1905.10887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1905.10887","doi":"https://doi.org/10.48550/arxiv.1905.10887","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.10887","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2971337561","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.10887.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.10887","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.10887","pdf_url":"https://arxiv.org/pdf/1905.10887","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2945027741.pdf","grobid_xml":"https://content.openalex.org/works/W2945027741.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1813659000","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1982214722","https://openalex.org/W2025720061","https://openalex.org/W2099057450","https://openalex.org/W2099471712","https://openalex.org/W2194775991","https://openalex.org/W2212660284","https://openalex.org/W2409550820","https://openalex.org/W2432004435","https://openalex.org/W2592101326","https://openalex.org/W2622068151","https://openalex.org/W2622263826","https://openalex.org/W2632772789","https://openalex.org/W2735642330","https://openalex.org/W2766527293","https://openalex.org/W2782010268","https://openalex.org/W2782980316","https://openalex.org/W2786691175","https://openalex.org/W2787579267","https://openalex.org/W2804123849","https://openalex.org/W2804161309","https://openalex.org/W2805984778","https://openalex.org/W2807747378","https://openalex.org/W2810979309","https://openalex.org/W2884805522","https://openalex.org/W2893749619","https://openalex.org/W2896687685","https://openalex.org/W2902630600","https://openalex.org/W2903135068","https://openalex.org/W2904367110","https://openalex.org/W2922386270","https://openalex.org/W2934761288","https://openalex.org/W2937274663","https://openalex.org/W2947590261","https://openalex.org/W2951004968","https://openalex.org/W2952185567","https://openalex.org/W2952583441","https://openalex.org/W2962785568","https://openalex.org/W2962837045","https://openalex.org/W2963139417","https://openalex.org/W2963636093","https://openalex.org/W2963981733","https://openalex.org/W6903428514"],"related_works":["https://openalex.org/W3017919939","https://openalex.org/W7052598941","https://openalex.org/W4396941607","https://openalex.org/W2965724622","https://openalex.org/W3210069274","https://openalex.org/W3091068658","https://openalex.org/W3133549907","https://openalex.org/W4309911437","https://openalex.org/W7222967426","https://openalex.org/W2592261558"],"abstract_inverted_index":{"Deep":[0],"generative":[1,69,81,164,195,241],"models":[2,70,165,196],"(DGMs)":[3],"of":[4,74,89,225,240],"images":[5],"are":[6,44],"now":[7],"sufficiently":[8],"mature":[9],"that":[10,42],"they":[11],"produce":[12],"nearly":[13],"photorealistic":[14],"samples":[15],"and":[16,54,80,105,136,148,154,162,176,203,221],"obtain":[17],"scores":[18],"similar":[19],"to":[20,109,158,198,236],"the":[21,46,86,107,159,200,208,245],"data":[22,47,104,201],"distribution":[23,48],"on":[24,35,112,117,184],"heuristics":[25],"such":[26,38,170,216],"as":[27,39,171,217],"Frechet":[28],"Inception":[29,218],"Distance":[30],"(FID).":[31],"These":[32],"results,":[33],"especially":[34],"large-scale":[36],"datasets":[37],"ImageNet,":[40],"suggest":[41],"DGMs":[43],"learning":[45],"in":[49,58,207,234],"a":[50,72,143],"perceptually":[51],"meaningful":[52],"space":[53],"can":[55],"be":[56],"used":[57],"downstream":[59],"tasks.":[60],"To":[61],"test":[62],"this":[63,94,118,185],"latter":[64],"hypothesis,":[65],"we":[66,121,211,243],"use":[67],"class-conditional":[68],"from":[71,166],"number":[73],"model":[75,168],"classes---variational":[76],"autoencoders,":[77],"autoregressive":[78],"models,":[79,242],"adversarial":[82],"networks":[83],"(GANs)---to":[84],"infer":[85],"class":[87],"labels":[88,111],"real":[90,113],"data.":[91,114],"We":[92],"perform":[93],"inference":[95],"by":[96,133,152],"training":[97],"an":[98],"image":[99],"classifier":[100,108],"using":[101,106,142],"only":[102],"synthetic":[103],"predict":[110],"The":[115],"performance":[116],"task,":[119],"which":[120,194],"call":[122],"Classification":[123],"Accuracy":[124],"Score":[125,219],"(CAS),":[126],"reveals":[127],"some":[128],"surprising":[129],"results":[130],"not":[131],"identified":[132],"traditional":[134,213],"metrics":[135,215],"constitute":[137],"our":[138],"contributions.":[139],"First,":[140],"when":[141,229],"state-of-the-art":[144],"GAN":[145,214],"(BigGAN-deep),":[146],"Top-1":[147],"Top-5":[149],"accuracy":[150],"decrease":[151],"27.9\\%":[153],"41.6\\%,":[155],"respectively,":[156],"compared":[157],"original":[160],"data;":[161],"conditional":[163],"other":[167],"classes,":[169],"Vector-Quantized":[172],"Variational":[173],"Autoencoder-2":[174],"(VQ-VAE-2)":[175],"Hierarchical":[177],"Autoregressive":[178],"Models":[179],"(HAMs),":[180],"substantially":[181],"outperform":[182],"GANs":[183],"benchmark.":[186],"Second,":[187],"CAS":[188,226],"automatically":[189],"surfaces":[190],"particular":[191],"classes":[192],"for":[193],"failed":[197],"capture":[199],"distribution,":[202],"were":[204],"previously":[205],"unknown":[206],"literature.":[209],"Third,":[210],"find":[212],"(IS)":[220],"FID":[222],"neither":[223],"predictive":[224],"nor":[227],"useful":[228],"evaluating":[230],"non-GAN":[231],"models.":[232],"Furthermore,":[233],"order":[235],"facilitate":[237],"better":[238],"diagnoses":[239],"open-source":[244],"proposed":[246],"metric.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":10}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-05-29T00:00:00"}