{"id":"https://openalex.org/W4385271055","doi":"https://doi.org/10.1145/3592133","title":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models","display_name":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models","publication_year":2023,"publication_date":"2023-07-26","ids":{"openalex":"https://openalex.org/W4385271055","doi":"https://doi.org/10.1145/3592133"},"language":"en","primary_location":{"id":"doi:10.1145/3592133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592133","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057080001","display_name":"Rinon Gal","orcid":"https://orcid.org/0000-0003-4875-965X"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Rinon Gal","raw_affiliation_strings":["NVIDIA Research, Tel Aviv, Israel","Tel Aviv University, Tel Aviv, Israel","Tel Aviv University, Tel Aviv, Israel NVIDIA Research, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel NVIDIA Research, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027063499","display_name":"Moab Arar","orcid":"https://orcid.org/0000-0001-8423-3538"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Moab Arar","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080909499","display_name":"Yuval Atzmon","orcid":"https://orcid.org/0000-0003-3817-3698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuval Atzmon","raw_affiliation_strings":["NVIDIA Research, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001922143","display_name":"Amit H. Bermano","orcid":"https://orcid.org/0000-0002-3592-1112"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Amit H. Bermano","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045719865","display_name":"Gal Chechik","orcid":"https://orcid.org/0000-0001-9164-5303"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gal Chechik","raw_affiliation_strings":["Bar-Ilan University, Tel Aviv, Israel","NVIDIA Research, Tel Aviv, Israel","NVIDIA Research, Tel Aviv, Israel Bar-Ilan University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]},{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel Bar-Ilan University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036688260","display_name":"Daniel Cohen\u2010Or","orcid":"https://orcid.org/0000-0001-6777-7445"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Daniel Cohen-Or","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057080001"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":16.7159,"has_fulltext":false,"cited_by_count":139,"citation_normalized_percentile":{"value":0.99513617,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"42","issue":"4","first_page":"1","last_page":"13"},"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":0.9987999796867371,"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":0.9987999796867371,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9961000084877014,"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/T11309","display_name":"Music and Audio Processing","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8407754302024841},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7631893157958984},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7571033239364624},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6689955592155457},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6259676218032837},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6223938465118408},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5767996907234192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5501922369003296},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5362659692764282},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.510403573513031},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4875344932079315},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37005043029785156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3368142247200012},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10458576679229736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407754302024841},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7631893157958984},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7571033239364624},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6689955592155457},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6259676218032837},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6223938465118408},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5767996907234192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501922369003296},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5362659692764282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.510403573513031},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4875344932079315},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37005043029785156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3368142247200012},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10458576679229736},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3592133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592133","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2166390741","https://openalex.org/W2401544298","https://openalex.org/W2519536754","https://openalex.org/W2560674852","https://openalex.org/W2886934227","https://openalex.org/W2893508485","https://openalex.org/W2961363059","https://openalex.org/W2962770929","https://openalex.org/W2963966654","https://openalex.org/W2966792645","https://openalex.org/W2985068832","https://openalex.org/W3034431451","https://openalex.org/W3034625979","https://openalex.org/W3035355202","https://openalex.org/W3035693354","https://openalex.org/W3036167779","https://openalex.org/W3122887115","https://openalex.org/W3162926177","https://openalex.org/W3174525637","https://openalex.org/W3180355996","https://openalex.org/W4242177601","https://openalex.org/W4286976841","https://openalex.org/W4312294878","https://openalex.org/W4312562701","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4312984277","https://openalex.org/W4313172370","https://openalex.org/W4386072096","https://openalex.org/W6779823529","https://openalex.org/W6795288823","https://openalex.org/W6912494966"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W2081900870","https://openalex.org/W3172493050","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W1536183945","https://openalex.org/W2593798266","https://openalex.org/W2070126461","https://openalex.org/W4385420271"],"abstract_inverted_index":{"Text-to-image":[0],"personalization":[1,28,179],"aims":[2],"to":[3,9,81,120,142,152,161,184],"teach":[4],"a":[5,60,66,75,103,107,111,115,124,130,163,167],"pre-trained":[6],"diffusion":[7],"model":[8,76,138,164],"reason":[10],"about":[11],"novel,":[12],"user":[13],"provided":[14],"concepts,":[15,158],"embedding":[16],"them":[17],"into":[18,123],"new":[19],"scenes":[20],"guided":[21],"by":[22,57],"natural":[23],"language":[24],"prompts.":[25],"However,":[26],"current":[27],"approaches":[29],"struggle":[30],"with":[31],"lengthy":[32],"training":[33,175],"times,":[34],"high":[35],"storage":[36],"requirements":[37],"or":[38],"loss":[39],"of":[40,63,106,132,156,182],"identity.":[41],"To":[42],"overcome":[43],"these":[44,148],"limitations,":[45],"we":[46,69,91],"propose":[47],"an":[48,96,101],"encoder-based":[49],"domain-tuning":[50],"approach.":[51],"Our":[52],"key":[53],"insight":[54],"is":[55,78],"that":[56,77,98,139],"underfitting":[58],"on":[59],"large":[61],"set":[62,131],"concepts":[64,85],"from":[65,86,110,180],"given":[67,112],"domain,":[68,113],"can":[70],"improve":[71],"generalization":[72],"and":[73,118,170,191],"create":[74],"more":[79],"amenable":[80],"quickly":[82],"adding":[83],"novel":[84],"the":[87,127,136,154],"same":[88],"domain.":[89],"Specifically,":[90],"employ":[92],"two":[93],"components:":[94],"First,":[95],"encoder":[97],"takes":[99],"as":[100,171,173],"input":[102],"single":[104,168],"image":[105,169],"target":[108],"concept":[109],"e.g.":[114],"specific":[116],"face,":[117],"learns":[119],"map":[121],"it":[122],"word-embedding":[125],"representing":[126],"concept.":[128],"Second,":[129],"regularized":[133],"weight-offsets":[134],"for":[135],"text-to-image":[137],"learn":[140],"how":[141],"effectively":[143],"injest":[144],"additional":[145],"concepts.":[146],"Together,":[147],"components":[149],"are":[150],"used":[151],"guide":[153],"learning":[155],"unseen":[157],"allowing":[159],"us":[160],"personalize":[162],"using":[165],"only":[166],"few":[172],"5":[174],"steps":[176],"---":[177],"accelerating":[178],"dozens":[181],"minutes":[183],"seconds":[185],",":[186],"while":[187],"preserving":[188],"quality.":[189],"Code":[190],"trained":[192],"encoders":[193],"will":[194],"be":[195],"available":[196],"at":[197],"our":[198],"project":[199],"page.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":76},{"year":2023,"cited_by_count":10}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}