{"id":"https://openalex.org/W4387635758","doi":"https://doi.org/10.48550/arxiv.2310.08381","title":"AutoVP: An Automated Visual Prompting Framework and Benchmark","display_name":"AutoVP: An Automated Visual Prompting Framework and Benchmark","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387635758","doi":"https://doi.org/10.48550/arxiv.2310.08381"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.08381","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08381","pdf_url":"https://arxiv.org/pdf/2310.08381","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/2310.08381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104182909","display_name":"Hsi-Ai Tsao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsao, Hsi-Ai","raw_affiliation_strings":["National Tsing Hua University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University ,","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076380995","display_name":"Lei Hsiung","orcid":"https://orcid.org/0000-0001-7065-2336","observed_orcids":["https://orcid.org/0000-0001-7065-2336"]},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsiung, Lei","raw_affiliation_strings":["Dartmouth College ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dartmouth College ,","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369","observed_orcids":["https://orcid.org/0000-0003-1039-8369","https://orcid.org/0009-0000-1440-7870","https://orcid.org/0009-0007-6751-1090","https://orcid.org/0009-0008-1182-583X"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Pin-Yu","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321843","display_name":"Sijia Liu","orcid":"https://orcid.org/0000-0003-2817-6991","observed_orcids":["https://orcid.org/0000-0003-2817-6991","https://orcid.org/0009-0003-8538-9528"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Sijia","raw_affiliation_strings":["Michigan State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University ,","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062800747","display_name":"Tsung-Yi Ho","orcid":"https://orcid.org/0000-0001-7348-5625","observed_orcids":["https://orcid.org/0000-0001-7348-5625"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ho, Tsung-Yi","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9951000213623047,"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":0.9951000213623047,"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":0.00430000014603138,"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":0.0003000000142492354,"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/visual-prompting","display_name":"visual prompting","score":0.996999979019165},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.8980000019073486},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.734000027179718},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4480000138282776},{"id":"https://openalex.org/keywords/pre-trained-vision-models","display_name":"pre-trained vision models","score":0.859000027179718},{"id":"https://openalex.org/keywords/label-mapping","display_name":"label mapping","score":0.6729999780654907},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.6959999799728394},{"id":"https://openalex.org/keywords/linear-probing","display_name":"linear probing","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8850787878036499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721750140190125},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7194163203239441},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6765610575675964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5642825365066528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5391867756843567},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5163675546646118},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4970109760761261},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.454792320728302},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44273343682289124},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4398537874221802},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4257819652557373},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4200338125228882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35811275243759155},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.08381","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08381","pdf_url":"https://arxiv.org/pdf/2310.08381","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.2310.08381","doi":"https://doi.org/10.48550/arxiv.2310.08381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.08381","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:2310.08381","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08381","pdf_url":"https://arxiv.org/pdf/2310.08381","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387635758.pdf","grobid_xml":"https://content.openalex.org/works/W4387635758.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411249748","https://openalex.org/W4416399821","https://openalex.org/W4386075538","https://openalex.org/W4417406160","https://openalex.org/W4407124431","https://openalex.org/W7152752365","https://openalex.org/W4403780788","https://openalex.org/W6910680991","https://openalex.org/W4312091889","https://openalex.org/W7204093793"],"abstract_inverted_index":{"Visual":[0],"prompting":[1],"(VP)":[2],"is":[3,180],"an":[4,49,153],"emerging":[5],"parameter-efficient":[6],"fine-tuning":[7],"approach":[8],"to":[9,14,126,140,173],"adapting":[10],"pre-trained":[11,87],"vision":[12],"models":[13],"solve":[15],"various":[16],"downstream":[17,61],"image-classification":[18,62],"tasks.":[19],"However,":[20],"there":[21],"has":[22],"hitherto":[23],"been":[24],"little":[25],"systematic":[26],"study":[27],"of":[28,32,80,86,137],"the":[29,77,81,84,115],"design":[30,56,73,161],"space":[31,74],"VP":[33,55,118,160],"and":[34,92,95,103,131,163],"no":[35],"clear":[36],"benchmark":[37,167],"for":[38,53,156],"evaluating":[39],"its":[40],"performance.":[41],"To":[42],"bridge":[43],"this":[44],"gap,":[45],"we":[46],"propose":[47],"AutoVP,":[48],"end-to-end":[50],"expandable":[51],"framework":[52],"automating":[54],"choices,":[57,162],"along":[58],"with":[59],"12":[60],"tasks":[63],"that":[64,112,168],"can":[65,169],"serve":[66],"as":[67,152,164],"a":[68,121,133,147,165],"holistic":[69],"VP-performance":[70],"benchmark.":[71],"Our":[72,107],"covers":[75],"1)":[76],"joint":[78],"optimization":[79],"prompts;":[82],"2)":[83],"selection":[85],"models,":[88],"including":[89,101],"image":[90],"classifiers":[91],"text-image":[93],"encoders;":[94],"3)":[96],"model":[97],"output":[98],"mapping":[99],"strategies,":[100],"nonparametric":[102],"trainable":[104],"label":[105],"mapping.":[106],"extensive":[108],"experimental":[109],"results":[110],"show":[111],"AutoVP":[113,144],"outperforms":[114],"best-known":[116],"current":[117],"methods":[119],"by":[120],"substantial":[122],"margin,":[123],"having":[124],"up":[125],"6.7%":[127],"improvement":[128],"in":[129],"accuracy;":[130],"attains":[132],"maximum":[134],"performance":[135],"increase":[136],"27.5%":[138],"compared":[139],"linear-probing":[141],"(LP)":[142],"baseline.":[143],"thus":[145],"makes":[146],"two-fold":[148],"contribution:":[149],"serving":[150],"both":[151],"efficient":[154],"tool":[155],"hyperparameter":[157],"tuning":[158],"on":[159],"comprehensive":[166],"reasonably":[170],"be":[171],"expected":[172],"accelerate":[174],"VP's":[175],"development.":[176],"The":[177],"source":[178],"code":[179],"available":[181],"at":[182],"https://github.com/IBM/AutoVP.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2023-10-14T00:00:00"}