{"id":"https://openalex.org/W4389364482","doi":"https://doi.org/10.48550/arxiv.2312.02139","title":"DiffiT: Diffusion Vision Transformers for Image Generation","display_name":"DiffiT: Diffusion Vision Transformers for Image Generation","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4389364482","doi":"https://doi.org/10.48550/arxiv.2312.02139"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.02139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.02139","pdf_url":"https://arxiv.org/pdf/2312.02139","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.02139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028525720","display_name":"Ali Hatamizadeh","orcid":"https://orcid.org/0000-0002-5349-1996"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hatamizadeh, Ali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008049062","display_name":"Jiaming Song","orcid":"https://orcid.org/0000-0002-1931-1699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Jiaming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667303","display_name":"Guilin Liu","orcid":"https://orcid.org/0000-0003-4286-5187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guilin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056503617","display_name":"Jan Kautz","orcid":"https://orcid.org/0000-0002-8830-429X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kautz, Jan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038984764","display_name":"Arash Vahdat","orcid":"https://orcid.org/0009-0005-9476-1306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vahdat, Arash","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028525720"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"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":0.9926000237464905,"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":0.9926000237464905,"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/T10862","display_name":"AI in cancer detection","score":0.9144999980926514,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9117000102996826,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7256091237068176},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.7144745588302612},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6653485298156738},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5816386938095093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5765242576599121},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4960852563381195},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4709630608558655},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.41068774461746216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38852038979530334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33244457840919495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256091237068176},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.7144745588302612},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6653485298156738},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5816386938095093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5765242576599121},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4960852563381195},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4709630608558655},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.41068774461746216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38852038979530334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33244457840919495},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.02139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.02139","pdf_url":"https://arxiv.org/pdf/2312.02139","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.02139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.02139","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.02139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.02139","pdf_url":"https://arxiv.org/pdf/2312.02139","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4313443006","https://openalex.org/W4380551139","https://openalex.org/W2945374968","https://openalex.org/W4317695495","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W4287117424","https://openalex.org/W4387506531"],"abstract_inverted_index":{"Diffusion":[0,56],"models":[1,102,144],"with":[2,89],"their":[3],"powerful":[4],"expressivity":[5],"and":[6,30,49,72,98,103,112,148],"high":[7],"sample":[8],"quality":[9],"have":[10],"achieved":[11],"State-Of-The-Art":[12],"(SOTA)":[13],"performance":[14,106],"in":[15,45,85],"the":[16,41,69,74],"generative":[17,47],"domain.":[18],"The":[19,119],"pioneering":[20],"Vision":[21,57],"Transformer":[22],"(ViT)":[23],"has":[24],"also":[25,95],"demonstrated":[26],"strong":[27],"modeling":[28],"capabilities":[29],"scalability,":[31],"especially":[32],"for":[33,65],"recognition":[34],"tasks.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,61],"study":[40],"effectiveness":[42],"of":[43,68,110,129],"ViTs":[44],"diffusion-based":[46],"learning":[48],"propose":[50,62,96],"a":[51,63,108,124],"new":[52,125],"model":[53,122],"denoted":[54],"as":[55,146],"Transformers":[58],"(DiffiT).":[59],"Specifically,":[60],"methodology":[64],"finegrained":[66],"control":[67],"denoising":[70],"process":[71],"introduce":[73],"Time-dependant":[75],"Multihead":[76],"Self":[77],"Attention":[78],"(TMSA)":[79],"mechanism.":[80],"DiffiT":[81,101,121],"is":[82],"surprisingly":[83],"effective":[84],"generating":[86],"high-fidelity":[87],"images":[88],"significantly":[90],"better":[91],"parameter":[92],"efficiency.":[93],"We":[94],"latent":[97],"image":[99],"space":[100],"show":[104],"SOTA":[105,126],"on":[107,131],"variety":[109],"class-conditional":[111],"unconditional":[113],"synthesis":[114],"tasks":[115],"at":[116],"different":[117],"resolutions.":[118],"Latent":[120],"achieves":[123],"FID":[127],"score":[128],"1.73":[130],"ImageNet256":[132],"dataset":[133],"while":[134],"having":[135],"19.85%,":[136],"16.88%":[137],"less":[138],"parameters":[139],"than":[140],"other":[141],"Transformer-based":[142],"diffusion":[143],"such":[145],"MDT":[147],"DiT,respectively.":[149],"Code:":[150],"https://github.com/NVlabs/DiffiT":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}