{"id":"https://openalex.org/W4387185291","doi":"https://doi.org/10.3233/faia230595","title":"Instance-Wise Adaptive Tuning and Caching for Vision-Language Models","display_name":"Instance-Wise Adaptive Tuning and Caching for Vision-Language Models","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185291","doi":"https://doi.org/10.3233/faia230595"},"language":"en","primary_location":{"id":"doi:10.3233/faia230595","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230595","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230595","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230595","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101250272","display_name":"Chunjin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjin Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617043","display_name":"Fanman Meng","orcid":"https://orcid.org/0000-0002-3016-2567"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fanman Meng","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396713","display_name":"Shuai Chen","orcid":"https://orcid.org/0009-0007-0434-2197"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030965835","display_name":"Mingyu Liu","orcid":"https://orcid.org/0009-0001-1427-9503"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457752","display_name":"Runtong Zhang","orcid":"https://orcid.org/0000-0002-8198-8457"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runtong Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100617043"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35875234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.995199978351593,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9779999852180481,"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/computer-science","display_name":"Computer science","score":0.8354635238647461},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6840387582778931},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6066065430641174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5722137093544006},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5710360407829285},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5633521676063538},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5560749769210815},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5518069863319397},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38061800599098206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3531462550163269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8354635238647461},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6840387582778931},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6066065430641174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722137093544006},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5710360407829285},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5633521676063538},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5560749769210815},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5518069863319397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38061800599098206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3531462550163269},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230595","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230595","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230595","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230595","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230595","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230595","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G3308342199","display_name":null,"funder_award_id":"62271119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8366541121","display_name":null,"funder_award_id":"2023NSFSC1972","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185291.pdf","grobid_xml":"https://content.openalex.org/works/W4387185291.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W24089286","https://openalex.org/W1846799578","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2753192188","https://openalex.org/W2947707615","https://openalex.org/W2953937638","https://openalex.org/W2964194231","https://openalex.org/W2987283559","https://openalex.org/W2991382858","https://openalex.org/W3005680577","https://openalex.org/W3035524453","https://openalex.org/W3044438666","https://openalex.org/W3094502228","https://openalex.org/W3096331697","https://openalex.org/W3098267758","https://openalex.org/W3110226019","https://openalex.org/W3119438769","https://openalex.org/W3135367836","https://openalex.org/W3166396011","https://openalex.org/W3173859428","https://openalex.org/W3174770825","https://openalex.org/W3177096435","https://openalex.org/W3184735396","https://openalex.org/W3198377975","https://openalex.org/W3205789812","https://openalex.org/W4221143399","https://openalex.org/W4221157622","https://openalex.org/W4226427271","https://openalex.org/W4239072543","https://openalex.org/W4281838252","https://openalex.org/W4285191490","https://openalex.org/W4286588515","https://openalex.org/W4292945941","https://openalex.org/W4297795751","https://openalex.org/W4309590308","https://openalex.org/W4310924287","https://openalex.org/W4312310776","https://openalex.org/W4313175608","https://openalex.org/W4321855229","https://openalex.org/W4386071547","https://openalex.org/W4386075882","https://openalex.org/W4386076397","https://openalex.org/W4386790226"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W3121791438","https://openalex.org/W2250140200"],"abstract_inverted_index":{"Large-scale":[0],"vision-language":[1],"models":[2],"(LVLMs)":[3],"pre-trained":[4],"on":[5,57,70,111,174,190],"massive":[6],"image-text":[7],"pairs":[8],"have":[9],"achieved":[10],"remarkable":[11],"success":[12],"in":[13],"visual":[14,134],"representations.":[15],"However,":[16],"existing":[17,169,188],"paradigms":[18],"to":[19,22,43,67,102,137,146,183],"transfer":[20],"LVLMs":[21],"downstream":[23],"tasks":[24],"encounter":[25],"two":[26,75,162],"primary":[27],"challenges.":[28],"Firstly,":[29],"the":[30,48,52,58,61,84,119,126,144,161,166],"text":[31,62],"features":[32,101],"remain":[33],"fixed":[34],"after":[35],"being":[36],"calculated":[37],"and":[38,63,88,117,130,140],"cannot":[39],"be":[40],"adjusted":[41],"according":[42],"image":[44,64,100,112],"features,":[45,65,113],"which":[46,98],"decreases":[47],"model\u2019s":[49,53,120,155],"adaptability.":[50,121],"Secondly,":[51],"output":[54,156],"solely":[55,173],"depends":[56],"similarity":[59],"between":[60,128],"leading":[66],"excessive":[68],"reliance":[69],"LVLMs.":[71,175],"To":[72],"address":[73],"these":[74],"challenges,":[76],"we":[77],"introduce":[78],"a":[79,132],"novel":[80],"two-branch":[81],"model":[82,145],"named":[83],"Instance-Wise":[85],"Adaptive":[86],"Tuning":[87],"Caching":[89],"(ATC).":[90],"Specifically,":[91],"one":[92],"branch":[93,124],"implements":[94],"our":[95,177],"proposed":[96],"ConditionNet,":[97],"guides":[99],"form":[103],"an":[104],"adaptive":[105],"textual":[106],"cache":[107],"that":[108,171],"adjusts":[109],"based":[110],"achieving":[114],"instance-wise":[115],"inference":[116],"improving":[118],"The":[122,154],"other":[123],"introduces":[125],"similarities":[127],"images":[129],"incorporates":[131],"learnable":[133],"cache,":[135],"designed":[136],"decouple":[138],"new":[139,148],"previous":[141],"knowledge,":[142],"allowing":[143],"acquire":[147],"knowledge":[149],"while":[150],"preserving":[151],"prior":[152],"knowledge.":[153],"is":[157],"jointly":[158],"determined":[159],"by":[160],"branches,":[163],"thus":[164],"overcoming":[165],"limitations":[167],"of":[168],"methods":[170,189],"rely":[172],"Additionally,":[176],"method":[178],"requires":[179],"limited":[180],"computing":[181],"resources":[182],"tune":[184],"parameters,":[185],"yet":[186],"outperforms":[187],"11":[191],"benchmark":[192],"datasets.":[193]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}