{"id":"https://openalex.org/W4415202836","doi":"https://doi.org/10.1109/iccv51701.2025.01450","title":"Att-Adapter: a Robust and Precise Domain-Specific Multi-Attributes T2i Diffusion Adapter Via Conditional Variational Autoencoder","display_name":"Att-Adapter: a Robust and Precise Domain-Specific Multi-Attributes T2i Diffusion Adapter Via Conditional Variational Autoencoder","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415202836","doi":"https://doi.org/10.1109/iccv51701.2025.01450"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.11937","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032095488","display_name":"Wonwoong Cho","orcid":"https://orcid.org/0000-0003-0898-0341"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wonwoong Cho","raw_affiliation_strings":["Purdue University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041192765","display_name":"Yanying Chen","orcid":"https://orcid.org/0000-0001-5034-5312"},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]},{"id":"https://openalex.org/I917207718","display_name":"Toyota Industries (United States)","ror":"https://ror.org/0132ebr60","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210145315","https://openalex.org/I917207718"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan-Ying Chen","raw_affiliation_strings":["Toyota Research Institute,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute,USA","institution_ids":["https://openalex.org/I4391768151","https://openalex.org/I917207718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046977124","display_name":"Matthew Klenk","orcid":null},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]},{"id":"https://openalex.org/I917207718","display_name":"Toyota Industries (United States)","ror":"https://ror.org/0132ebr60","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210145315","https://openalex.org/I917207718"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Klenk","raw_affiliation_strings":["Toyota Research Institute,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute,USA","institution_ids":["https://openalex.org/I4391768151","https://openalex.org/I917207718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074209565","display_name":"David I. Inouye","orcid":"https://orcid.org/0000-0003-4493-3358"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David I. Inouye","raw_affiliation_strings":["Purdue University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100712432","display_name":"Yanxia Zhang","orcid":"https://orcid.org/0000-0002-6610-5265"},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]},{"id":"https://openalex.org/I917207718","display_name":"Toyota Industries (United States)","ror":"https://ror.org/0132ebr60","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210145315","https://openalex.org/I917207718"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanxia Zhang","raw_affiliation_strings":["Toyota Research Institute,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute,USA","institution_ids":["https://openalex.org/I4391768151","https://openalex.org/I917207718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24883834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15626","last_page":"15635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4336000084877014,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4336000084877014,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.40299999713897705,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.38019999861717224,"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/autoencoder","display_name":"Autoencoder","score":0.835099995136261},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6097000241279602},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.46149998903274536},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4544000029563904},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.4415000081062317},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4097999930381775},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.40939998626708984}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.835099995136261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715399980545044},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303000211715698},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3765000104904175},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C27753989","wikidata":"https://www.wikidata.org/wiki/Q284885","display_name":"Superposition principle","level":2,"score":0.25}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.11937","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11937","pdf_url":"https://arxiv.org/pdf/2503.11937","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,"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.2503.11937","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.11937","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.11937","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11937","pdf_url":"https://arxiv.org/pdf/2503.11937","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-Image":[0],"(T2I)":[1],"Diffusion":[2],"Models":[3],"have":[4],"achieved":[5],"remarkable":[6],"performance":[7],"in":[8,24,63,140],"generating":[9],"high":[10],"quality":[11],"images.":[12],"However,":[13],"enabling":[14],"precise":[15],"control":[16,62,72,150],"of":[17,77,124],"continuous":[18,142],"attributes,":[19,158],"especially":[20],"multiple":[21,86,101,157,178],"attributes":[22,103,179],"simultaneously,":[23],"a":[25,41,53,70,75,148,181],"new":[26],"domain":[27,102],"(e.g.,":[28],"numeric":[29],"values":[30],"like":[31],"eye":[32],"openness":[33],"or":[34],"car":[35],"width)":[36],"with":[37,104],"text-only":[38],"guidance":[39],"remains":[40],"significant":[42],"challenge.":[43],"To":[44],"address":[45],"this,":[46],"we":[47],"introduce":[48,109],"the":[49,92,100,115,121,125],"Attribute":[50],"(Att)":[51],"Adapter,":[52],"novel":[54],"plug-and-play":[55],"module":[56,96],"designed":[57],"to":[58,97,114,117,177],"enable":[59],"fine-grained,":[60],"multi-attributes":[61],"pretrained":[64],"diffusion":[65],"models.":[66],"Our":[67],"approach":[68],"learns":[69],"single":[71,182],"adapter":[73],"from":[74],"set":[76],"sample":[78],"images":[79],"that":[80,134],"can":[81],"be":[82],"unpaired":[83],"and":[84,152,173],"contain":[85],"visual":[87,126],"attributes.":[88,143],"The":[89],"Att-Adapter":[90,116,135,163],"leverages":[91],"decoupled":[93],"cross":[94],"attention":[95],"naturally":[98],"harmonize":[99],"text":[105],"conditioning.":[106],"We":[107],"further":[108],"Conditional":[110],"Variational":[111],"Autoencoder":[112],"(CVAE)":[113],"mitigate":[118],"overfitting,":[119],"matching":[120],"diverse":[122],"nature":[123],"world.":[127],"Evaluations":[128],"on":[129],"two":[130],"public":[131],"datasets":[132],"show":[133],"outperforms":[136],"all":[137],"LoRA-based":[138],"baselines":[139],"controlling":[141],"Additionally,":[144],"our":[145],"method":[146],"enables":[147],"broader":[149],"range":[151],"also":[153],"improves":[154],"disentanglement":[155],"across":[156],"surpassing":[159],"StyleGAN-based":[160],"techniques.":[161],"Notably,":[162],"is":[164,174],"flexible,":[165],"requiring":[166],"no":[167],"paired":[168],"synthetic":[169],"data":[170],"for":[171],"training,":[172],"easily":[175],"scalable":[176],"within":[180],"model.":[183]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-16T00:00:00"}