乐胖代购免代理版

{"id":"https://openalex.org/W4313921076","doi":"https://doi.org/10.48550/arxiv.2301.02419","title":"Exploring Efficient Few-shot Adaptation for Vision Transformers","display_name":"Exploring Efficient Few-shot Adaptation for Vision Transformers","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4313921076","doi":"https://doi.org/10.48550/arxiv.2301.02419"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2301.02419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2301.02419","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101908952","display_name":"Chengming Xu","orcid":"https://orcid.org/0000-0003-3891-2227"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chengming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032912558","display_name":"Siqian Yang","orcid":"https://orcid.org/0000-0001-6100-3414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Siqian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yabiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009597034","display_name":"Zhanxiong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhanxiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yanwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Xiangyang","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.917444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":92},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9989,"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":0.9989,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9605,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9481,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain Adaptation","score":0.59884727},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization","score":0.46720952},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.45332047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76673365},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6352275},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.62204015},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.59884727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53570026},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.50830907},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.46720952},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.45332047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38231304},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2301.02419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.02419","pdf_url":"http://arxiv.org/pdf/2301.02419","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2301.02419","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2301.02419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.67}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385305499","https://openalex.org/W4245066656","https://openalex.org/W3196321793","https://openalex.org/W3080705045","https://openalex.org/W2507465767","https://openalex.org/W2385527937","https://openalex.org/W2373597927","https://openalex.org/W2142481367","https://openalex.org/W2047674875","https://openalex.org/W2005880840"],"abstract_inverted_index":{"The":[0,117],"task":[1,136],"of":[2,22,60,176,219,245],"Few-shot":[3],"Learning":[4],"(FSL)":[5],"aims":[6],"to":[7,51,72,88,148,157,161,180,241],"do":[8],"the":[9,20,49,91,114,122,135,144,163,171,174,182,193,199,213,216,225,234,243],"inference":[10],"on":[11,57,79,233],"novel":[12,103,189,208],"categories":[13,27],"containing":[14,28],"only":[15],"few":[16,54],"labeled":[17,30],"examples,":[18],"with":[19,53,165],"help":[21],"knowledge":[23],"learned":[24],"from":[25,121,198],"base":[26,187],"abundant":[29],"training":[31],"samples.":[32],"While":[33],"there":[34],"are":[35,155],"numerous":[36],"works":[37],"into":[38],"FSL":[39,52,95,115],"task,":[40],"Vision":[41],"Transformers":[42],"(ViTs)":[43],"have":[44,69],"rarely":[45],"been":[46,70],"taken":[47],"as":[48],"backbone":[50,62,138],"trials":[55],"focusing":[56],"naive":[58],"finetuning":[59,111],"whole":[61],"or":[63,75],"classification":[64],"layer.}":[65],"Essentially,":[66],"despite":[67],"ViTs":[68,92,112],"shown":[71],"enjoy":[73],"comparable":[74],"even":[76],"better":[77],"performance":[78,232],"other":[80],"vision":[81],"tasks,":[82],"it":[83],"is":[84,146],"still":[85],"very":[86],"nontrivial":[87],"efficiently":[89],"finetune":[90],"in":[93,113,142,173],"real-world":[94],"scenarios.":[96],"To":[97,191],"this":[98],"end,":[99],"we":[100,169,204],"propose":[101,206],"a":[102,207],"efficient":[104],"Transformer":[105],"Tuning":[106,127],"(eTT)":[107],"method":[108,229],"that":[109,154],"facilitates":[110],"tasks.":[116],"key":[118,150],"novelties":[119],"come":[120],"newly":[123],"presented":[124],"Attentive":[125],"Prefix":[126],"(APT)":[128],"and":[129,137,151,188,221],"Domain":[130],"Residual":[131],"Adapter":[132],"(DRA)":[133],"for":[134],"tuning,":[139],"individually.":[140],"Specifically,":[141],"APT,":[143],"prefix":[145,220],"projected":[147,217],"new":[149],"value":[152],"pairs":[153],"attached":[156],"each":[158],"self-attention":[159],"layer":[160],"provide":[162],"model":[164],"task-specific":[166,201],"information.":[167],"Moreover,":[168],"design":[170],"DRA":[172],"form":[175],"learnable":[177],"offset":[178],"vectors":[179],"handle":[181],"potential":[183],"domain":[184],"gaps":[185],"between":[186,215],"data.":[190],"ensure":[192],"APT":[194],"would":[195],"not":[196],"deviate":[197],"initial":[200,222],"information":[202],"much,":[203],"further":[205],"prototypical":[209],"regularization,":[210],"which":[211],"maximizes":[212],"similarity":[214],"distribution":[218],"prototypes,":[223],"regularizing":[224],"update":[226],"procedure.":[227],"Our":[228],"receives":[230],"outstanding":[231],"challenging":[235],"Meta-Dataset.":[236],"We":[237],"conduct":[238],"extensive":[239],"experiments":[240],"show":[242],"efficacy":[244],"our":[246],"model.":[247]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4313921076","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2025-04-20T23:45:23.405893","created_date":"2023-01-10"}