{"id":"https://openalex.org/W4378945342","doi":"https://doi.org/10.48550/arxiv.2305.18993","title":"ConES: Concept Embedding Search for Parameter Efficient Tuning Large Vision Language Models","display_name":"ConES: Concept Embedding Search for Parameter Efficient Tuning Large Vision Language Models","publication_year":2023,"publication_date":"2023-05-30","ids":{"openalex":"https://openalex.org/W4378945342","doi":"https://doi.org/10.48550/arxiv.2305.18993"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.18993","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18993","pdf_url":"https://arxiv.org/pdf/2305.18993","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.18993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060429045","display_name":"Huahui Yi","orcid":"https://orcid.org/0009-0007-9361-5491","observed_orcids":["https://orcid.org/0009-0007-9361-5491"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I2800091995","display_name":"West China Medical Center of Sichuan University","ror":"https://ror.org/040nggs60","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I24185976","https://openalex.org/I2800091995"]},{"id":"https://openalex.org/I4210089761","display_name":"West China Hospital of Sichuan University","ror":"https://ror.org/007mrxy13","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi, Huahui","raw_affiliation_strings":["West China Biomedical Big Data Center , West China Hospital , Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"West China Biomedical Big Data Center , West China Hospital , Sichuan University","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I2800091995","https://openalex.org/I4210089761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060788747","display_name":"Ziyuan Qin","orcid":"https://orcid.org/0009-0001-1013-4622","observed_orcids":["https://orcid.org/0009-0001-1013-4622"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I2800091995","display_name":"West China Medical Center of Sichuan University","ror":"https://ror.org/040nggs60","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I24185976","https://openalex.org/I2800091995"]},{"id":"https://openalex.org/I4210089761","display_name":"West China Hospital of Sichuan University","ror":"https://ror.org/007mrxy13","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin, Ziyuan","raw_affiliation_strings":["West China Biomedical Big Data Center , West China Hospital , Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"West China Biomedical Big Data Center , West China Hospital , Sichuan University","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I2800091995","https://openalex.org/I4210089761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407852","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-1960-0992","observed_orcids":["https://orcid.org/0000-0002-1960-0992","https://orcid.org/0000-0002-9590-1906","https://orcid.org/0009-0009-8295-9963","https://orcid.org/0000-0003-4208-7477"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I2800091995","display_name":"West China Medical Center of Sichuan University","ror":"https://ror.org/040nggs60","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I24185976","https://openalex.org/I2800091995"]},{"id":"https://openalex.org/I4210089761","display_name":"West China Hospital of Sichuan University","ror":"https://ror.org/007mrxy13","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Wei","raw_affiliation_strings":["School of Biomedical Engineering & Suzhou Institute for Advanced Research , USTC","West China Biomedical Big Data Center , West China Hospital , Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering & Suzhou Institute for Advanced Research , USTC","institution_ids":[]},{"raw_affiliation_string":"West China Biomedical Big Data Center , West China Hospital , Sichuan University","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I2800091995","https://openalex.org/I4210089761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112926908","display_name":"Miaotian Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Miaotian","raw_affiliation_strings":["School of Artificial Intelligence , BUPT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , BUPT","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366746","display_name":"Kun Wang","orcid":"https://orcid.org/0009-0008-4856-8806","observed_orcids":["https://orcid.org/0009-0008-4856-8806"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Kun","raw_affiliation_strings":["School of Data Science , USTC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , USTC","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066553616","display_name":"Shaoting Zhang","orcid":"https://orcid.org/0000-0002-8719-448X","observed_orcids":["https://orcid.org/0000-0002-8719-448X"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shaoting","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456986","display_name":"Kang Li","orcid":"https://orcid.org/0000-0002-8136-9816","observed_orcids":["https://orcid.org/0000-0002-8136-9816","https://orcid.org/0000-0001-6218-5715","https://orcid.org/0009-0004-4825-8438"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013010213","display_name":"Qicheng Lao","orcid":"https://orcid.org/0000-0002-6032-8548","observed_orcids":["https://orcid.org/0000-0002-6032-8548"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lao, Qicheng","raw_affiliation_strings":["School of Artificial Intelligence , BUPT","Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , BUPT","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0024999999441206455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0019000000320374966,"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/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.7310000061988831},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8970000147819519},{"id":"https://openalex.org/keywords/prompt-tuning","display_name":"prompt tuning","score":0.8029999732971191},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.6890000104904175},{"id":"https://openalex.org/keywords/instance-segmentation","display_name":"instance segmentation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/medical-image-synthesis","display_name":"medical image synthesis","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127086162567139},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7494322657585144},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7438360452651978},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5830327272415161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105317831039429},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5013954639434814},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.43355000019073486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3278788924217224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1954827904701233},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.18993","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18993","pdf_url":"https://arxiv.org/pdf/2305.18993","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.2305.18993","doi":"https://doi.org/10.48550/arxiv.2305.18993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.18993","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:2305.18993","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18993","pdf_url":"https://arxiv.org/pdf/2305.18993","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378945342.pdf","grobid_xml":"https://content.openalex.org/works/W4378945342.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6885035331","https://openalex.org/W7223124031","https://openalex.org/W4390874393","https://openalex.org/W4393146196","https://openalex.org/W4389471427","https://openalex.org/W7160349016","https://openalex.org/W4411016484","https://openalex.org/W4417223873","https://openalex.org/W4396914122","https://openalex.org/W7167272186"],"abstract_inverted_index":{"Large":[0],"pre-trained":[1,221],"vision-language":[2],"models":[3,223],"have":[4],"shown":[5],"great":[6],"prominence":[7],"in":[8,182,214,242,266],"transferring":[9],"pre-acquired":[10],"knowledge":[11],"to":[12,116,144,166,178,200],"various":[13],"domains":[14],"and":[15,45,86,104,238,253],"downstream":[16,246],"tasks":[17,247],"with":[18,67],"appropriate":[19],"prompting":[20],"or":[21,50],"tuning.":[22],"Existing":[23],"prevalent":[24],"tuning":[25,62,106,203,237],"methods":[26,73,204,241],"can":[27,210,233],"be":[28,211],"generally":[29],"categorized":[30],"into":[31],"three":[32],"genres:":[33],"1)":[34],"prompt":[35,40,61,65,113,133,236],"engineering":[36],"by":[37,131],"creating":[38],"suitable":[39],"texts,":[41],"which":[42,56],"is":[43,57,198],"time-consuming":[44],"requires":[46],"domain":[47],"expertise;":[48],"2)":[49],"simply":[51],"fine-tuning":[52,219],"the":[53,68,76,81,93,96,117,137,140,146,149,160,170,191,206,215,220,235,271],"whole":[54],"model,":[55],"extremely":[58],"inefficient;":[59],"3)":[60],"through":[63,152],"parameterized":[64],"embeddings":[66,114,134,209],"text":[69,77,98,141,161],"encoder.":[70],"Nevertheless,":[71],"all":[72],"rely":[74],"on":[75],"encoder":[78,99,142],"for":[79,100,185,224,263],"bridging":[80],"modality":[82,151],"gap":[83],"between":[84],"vision":[85],"language.":[87],"In":[88],"this":[89],"work,":[90],"we":[91,123,163],"question":[92],"necessity":[94],"of":[95,139,148,155,218,245],"cumbersome":[97],"a":[101,125,153,243],"more":[102,111],"lightweight":[103],"efficient":[105],"paradigm":[107],"as":[108,110,270],"well":[109],"representative":[112],"closer":[115],"image":[118,150,254],"representations.":[119],"To":[120],"achieve":[121],"this,":[122],"propose":[124],"Concept":[126],"Embedding":[127],"Search":[128],"(ConES)":[129],"approach":[130,197,232,257],"optimizing":[132],"--":[135,143],"without":[136,189],"need":[138],"capture":[145],"'concept'":[147],"variety":[154,244],"task":[156],"objectives.":[157],"By":[158],"dropping":[159],"encoder,":[162],"are":[164],"able":[165],"significantly":[167],"speed":[168],"up":[169],"learning":[171],"process,":[172],"\\eg,":[173],"from":[174],"about":[175],"an":[176],"hour":[177],"just":[179],"ten":[180],"minutes":[181],"our":[183,195,231],"experiments":[184,228],"personalized":[186],"text-to-image":[187],"generation":[188,192],"impairing":[190],"quality.":[193],"Moreover,":[194],"proposed":[196],"orthogonal":[199],"current":[201],"existing":[202],"since":[205],"searched":[207],"concept":[208],"further":[212],"utilized":[213],"next":[216],"stage":[217],"large":[222],"boosting":[225],"performance.":[226],"Extensive":[227],"show":[229],"that":[230],"beat":[234],"textual":[239],"inversion":[240],"including":[248],"objection":[249],"detection,":[250],"instance":[251],"segmentation,":[252],"generation.":[255],"Our":[256],"also":[258],"shows":[259],"better":[260],"generalization":[261],"capability":[262],"unseen":[264],"concepts":[265],"specialized":[267],"domains,":[268],"such":[269],"medical":[272],"domain.":[273]},"counts_by_year":[],"updated_date":"2026-10-04T09:36:47.201465","created_date":"2023-06-01T00:00:00"}