{"id":"https://openalex.org/W4281847696","doi":"https://doi.org/10.48550/arxiv.2206.02262","title":"Diffusion-GAN: Training GANs with Diffusion","display_name":"Diffusion-GAN: Training GANs with Diffusion","publication_year":2022,"publication_date":"2022-06-05","ids":{"openalex":"https://openalex.org/W4281847696","doi":"https://doi.org/10.48550/arxiv.2206.02262"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.02262","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02262","pdf_url":"https://arxiv.org/pdf/2206.02262","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/2206.02262","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100418321","display_name":"Zhendong Wang","orcid":"https://orcid.org/0000-0002-0647-3808","observed_orcids":["https://orcid.org/0000-0002-0647-3808","https://orcid.org/0009-0004-0116-9745"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Zhendong","raw_affiliation_strings":["Microsoft Azure AI","The University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure AI","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077499817","display_name":"Huangjie Zheng","orcid":"https://orcid.org/0000-0003-0508-5034","observed_orcids":["https://orcid.org/0000-0003-0508-5034","https://orcid.org/0009-0004-4910-5679"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Huangjie","raw_affiliation_strings":["Microsoft Azure AI","The University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure AI","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785116","display_name":"Pengcheng He","orcid":"https://orcid.org/0000-0003-3305-952X","observed_orcids":["https://orcid.org/0000-0003-3305-952X"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He, Pengcheng","raw_affiliation_strings":["Microsoft Azure AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure AI","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051745436","display_name":"Weizhu Chen","orcid":"https://orcid.org/0000-0003-4196-7229","observed_orcids":["https://orcid.org/0000-0003-4196-7229"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Weizhu","raw_affiliation_strings":["Microsoft Azure AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure AI","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010394308","display_name":"Mingyuan Zhou","orcid":"https://orcid.org/0000-0002-4253-2780","observed_orcids":["https://orcid.org/0000-0002-4253-2780"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Mingyuan","raw_affiliation_strings":["The University of Texas at Austin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin ,","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":253,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.0,"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/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.8989999890327454},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.652999997138977},{"id":"https://openalex.org/keywords/gan-training-stability","display_name":"GAN training stability","score":0.8059999942779541},{"id":"https://openalex.org/keywords/forward-diffusion","display_name":"forward diffusion","score":0.6579999923706055},{"id":"https://openalex.org/keywords/gaussian-mixture-noise","display_name":"Gaussian mixture noise","score":0.7250000238418579},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.671999990940094}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9819082021713257},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.7826944589614868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796475887298584},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6902526617050171},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6603742837905884},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.6369604468345642},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4368695616722107},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41262170672416687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3770766258239746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36324357986450195},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.11747786402702332},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10733899474143982},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08178132772445679},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C3017618536","wikidata":"https://www.wikidata.org/wiki/Q304994","display_name":"Innovation diffusion","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.02262","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02262","pdf_url":"https://arxiv.org/pdf/2206.02262","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.2206.02262","doi":"https://doi.org/10.48550/arxiv.2206.02262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.02262","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.02262","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02262","pdf_url":"https://arxiv.org/pdf/2206.02262","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":[{"id":"https://openalex.org/G1770015890","display_name":"Collaborative Research: III: Medium: Conditional Transport: Theory, Methods, Computation, and Applications","funder_award_id":"2212418","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281847696.pdf","grobid_xml":"https://content.openalex.org/works/W4281847696.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W967544008","https://openalex.org/W2173520492","https://openalex.org/W2411541852","https://openalex.org/W2412320034","https://openalex.org/W2619903301","https://openalex.org/W2893749619","https://openalex.org/W3092442149","https://openalex.org/W3119800657","https://openalex.org/W3140633421","https://openalex.org/W3165905282","https://openalex.org/W4221146050","https://openalex.org/W4224035735","https://openalex.org/W4226125322","https://openalex.org/W4226376398","https://openalex.org/W4300973224"],"related_works":["https://openalex.org/W4387498356","https://openalex.org/W2949277570","https://openalex.org/W3121258398","https://openalex.org/W3035872583","https://openalex.org/W4290714076","https://openalex.org/W4309074705","https://openalex.org/W4404314422","https://openalex.org/W3212103317","https://openalex.org/W4417247054","https://openalex.org/W7164931728"],"abstract_inverted_index":{"Generative":[0],"adversarial":[1],"networks":[2],"(GANs)":[3],"are":[4,73],"challenging":[5],"to":[6,44,96,126,146,151],"train":[7],"stably,":[8],"and":[9,64,70,91,130,143,181],"a":[10,34,40,60,65,87],"promising":[11],"remedy":[12],"of":[13,52,161],"injecting":[14],"instance":[15,48],"noise":[16,129],"into":[17],"the":[18,68,76,92,98,103,111,117,128,137,147,153,159],"discriminator":[19,94],"input":[20],"has":[21],"not":[22],"been":[23],"very":[24],"effective":[25],"in":[26],"practice.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"propose":[32],"Diffusion-GAN,":[33],"novel":[35],"GAN":[36,165],"framework":[37],"that":[38,136,171],"leverages":[39],"forward":[41,118],"diffusion":[42,58,61,79,83,119],"chain":[43],"generate":[45],"Gaussian-mixture":[46],"distributed":[47],"noise.":[49],"Diffusion-GAN":[50,162],"consists":[51],"three":[53],"components,":[54],"including":[55],"an":[56],"adaptive":[57,78],"process,":[59],"timestep-dependent":[62,93,139],"discriminator,":[63],"generator.":[66],"Both":[67],"observed":[69],"generated":[71,105],"data":[72,101,131,155,182],"diffused":[74,99,104],"by":[75,114],"same":[77],"process.":[80],"At":[81],"each":[82],"timestep,":[84],"there":[85],"is":[86,123],"different":[88],"noise-to-data":[89],"ratio":[90],"learns":[95,109],"distinguish":[97],"real":[100],"from":[102,110],"data.":[106],"The":[107],"generator":[108],"discriminator's":[112,138],"feedback":[113],"backpropagating":[115],"through":[116],"chain,":[120],"whose":[121],"length":[122],"adaptively":[124],"adjusted":[125],"balance":[127],"levels.":[132],"We":[133,157],"theoretically":[134],"show":[135],"strategy":[140],"gives":[141],"consistent":[142],"helpful":[144],"guidance":[145],"generator,":[148],"enabling":[149],"it":[150,172],"match":[152],"true":[154],"distribution.":[156],"demonstrate":[158],"advantages":[160],"over":[163],"strong":[164],"baselines":[166],"on":[167],"various":[168],"datasets,":[169],"showing":[170],"can":[173],"produce":[174],"more":[175],"realistic":[176],"images":[177],"with":[178],"higher":[179],"stability":[180],"efficiency":[183],"than":[184],"state-of-the-art":[185],"GANs.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":76},{"year":2024,"cited_by_count":83},{"year":2023,"cited_by_count":55},{"year":2022,"cited_by_count":9}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-06-13T00:00:00"}