{"id":"https://openalex.org/W4367190852","doi":"https://doi.org/10.48550/arxiv.2304.13639","title":"PVP: Pre-trained Visual Parameter-Efficient Tuning","display_name":"PVP: Pre-trained Visual Parameter-Efficient Tuning","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367190852","doi":"https://doi.org/10.48550/arxiv.2304.13639"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.13639","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13639","pdf_url":"https://arxiv.org/pdf/2304.13639","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/2304.13639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100540442","display_name":"Zhao Song","orcid":"https://orcid.org/0000-0001-5263-7044","observed_orcids":["https://orcid.org/0000-0001-5263-7044"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Zhao","raw_affiliation_strings":["Defense Innovation Institute , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002669383","display_name":"Ke Yang","orcid":"https://orcid.org/0000-0002-1870-1134","observed_orcids":["https://orcid.org/0000-0002-1870-1134","https://orcid.org/0009-0000-4109-622X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ke","raw_affiliation_strings":["Defense Innovation Institute , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103181621","display_name":"Naiyang Guan","orcid":"https://orcid.org/0000-0001-9314-2929","observed_orcids":["https://orcid.org/0000-0001-9314-2929"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Naiyang","raw_affiliation_strings":["Defense Innovation Institute , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370140","display_name":"Junjie Zhu","orcid":"https://orcid.org/0000-0001-7503-4502","observed_orcids":["https://orcid.org/0000-0001-7503-4502","https://orcid.org/0000-0002-8102-6661"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Junjie","raw_affiliation_strings":["Defense Innovation Institute , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiao, Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao, Peng","raw_affiliation_strings":["National University of Defense Technology , Changsha , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology , Changsha , China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036921959","display_name":"Qingyong Hu","orcid":"https://orcid.org/0000-0003-0337-9207","observed_orcids":["https://orcid.org/0000-0003-0337-9207","https://orcid.org/0000-0002-8719-7816"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Qingyong","raw_affiliation_strings":["National University of Defense Technology , Changsha , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology , Changsha , China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9907000064849854,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9907000064849854,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.009200000204145908,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":9.999999747378752e-05,"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/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.972000002861023},{"id":"https://openalex.org/keywords/visual-prompt-tuning","display_name":"visual prompt tuning","score":0.7919999957084656},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.9070000052452087},{"id":"https://openalex.org/keywords/fine-grained-image-classification","display_name":"fine-grained image classification","score":0.9100000262260437},{"id":"https://openalex.org/keywords/low-data-regimes","display_name":"low-data regimes","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8243492841720581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013005256652832},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7745855450630188},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5911464095115662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213819146156311},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4493907690048218},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17718976736068726},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.17661237716674805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07434970140457153},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2304.13639","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13639","pdf_url":"https://arxiv.org/pdf/2304.13639","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2304.13639","doi":"https://doi.org/10.48550/arxiv.2304.13639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.13639","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.13639","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13639","pdf_url":"https://arxiv.org/pdf/2304.13639","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5254524242","display_name":null,"funder_award_id":"62006241","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5432501813","display_name":null,"funder_award_id":"61902415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367190852.pdf","grobid_xml":"https://content.openalex.org/works/W4367190852.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1,63,155,179,184],"transformers":[2],"have":[3,48],"demonstrated":[4],"remarkable":[5],"success":[6],"in":[7,153],"various":[8],"computer":[9],"vision":[10],"tasks.":[11,193],"However,":[12],"it":[13],"is":[14,111,137],"still":[15,95],"highly":[16],"challenging":[17],"to":[18,27,89,105,140,187],"fully":[19],"fine-tune":[20],"these":[21,67],"models":[22,64],"for":[23],"downstream":[24,101,192],"tasks":[25],"due":[26,139],"their":[28],"high":[29],"computational":[30],"and":[31,44,53,65,175,202],"storage":[32,54],"costs.":[33],"Recently,":[34],"Parameter-Efficient":[35],"Tuning":[36,42,166],"(PETuning)":[37],"techniques,":[38],"e.g.,":[39],"Visual":[40,163,199],"Prompt":[41],"(VPT)":[43],"Low-Rank":[45],"Adaptation":[46],"(LoRA),":[47],"significantly":[49,210],"reduced":[50],"the":[51,62,79,134,141,154,170,178,183],"computation":[52],"cost":[55],"by":[56],"inserting":[57],"lightweight":[58],"prompt":[59,68,146],"modules":[60,69,173,180],"into":[61],"tuning":[66,172,190],"with":[70,182],"a":[71,85,97,161],"small":[72],"number":[73],"of":[74,100,144],"trainable":[75],"parameters,":[76],"while":[77],"keeping":[78],"transformer":[80,185],"backbone":[81,186],"frozen.":[82],"Although":[83],"only":[84,120],"few":[86],"parameters":[87],"need":[88],"be":[90],"adjusted,":[91],"most":[92],"PETuning":[93,213],"methods":[94],"require":[96],"significant":[98],"amount":[99],"task":[102],"training":[103],"data":[104],"achieve":[106],"good":[107],"results.":[108],"The":[109],"performance":[110,136],"inadequate":[112],"on":[113,191,196],"low-data":[114],"regimes,":[115],"especially":[116],"when":[117],"there":[118],"are":[119],"one":[121],"or":[122],"two":[123],"examples":[124],"per":[125],"class.":[126],"To":[127],"this":[128],"end,":[129],"we":[130,159],"first":[131,174],"empirically":[132],"identify":[133],"poor":[135],"mainly":[138],"inappropriate":[142],"way":[143],"initializing":[145],"modules,":[147],"which":[148,168],"has":[149],"also":[150],"been":[151],"verified":[152],"language":[156],"models.":[157],"Next,":[158],"propose":[160],"Pre-trained":[162],"Parameter-efficient":[164],"(PVP)":[165],"framework,":[167],"pre-trains":[169],"parameter-efficient":[171,189],"then":[176],"leverages":[177],"along":[181],"perform":[188],"Experiment":[194],"results":[195],"five":[197],"Fine-Grained":[198],"Classification":[200],"(FGVC)":[201],"VTAB-1k":[203],"datasets":[204],"demonstrate":[205],"that":[206],"our":[207],"proposed":[208],"method":[209],"outperforms":[211],"state-of-the-art":[212],"methods.":[214]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}