{"id":"https://openalex.org/W4402509848","doi":"https://doi.org/10.1109/tpami.2024.3460180","title":"Tuning Vision-Language Models With Multiple Prototypes Clustering","display_name":"Tuning Vision-Language Models With Multiple Prototypes Clustering","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4402509848","doi":"https://doi.org/10.1109/tpami.2024.3460180","pmid":"https://pubmed.ncbi.nlm.nih.gov/39269797"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3460180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3460180","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101135616","display_name":"Meng-Hao Guo","orcid":"https://orcid.org/0000-0002-4128-4594"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng-Hao Guo","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728379","display_name":"Yi Zhang","orcid":"https://orcid.org/0009-0009-6545-4672"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067592804","display_name":"Tai\u2010Jiang Mu","orcid":"https://orcid.org/0000-0002-9197-346X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tai-Jiang Mu","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000467703","display_name":"Xiaolei Huang","orcid":"https://orcid.org/0000-0003-2338-6535"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharon X. Huang","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037233582","display_name":"Shi\u2010Min Hu","orcid":"https://orcid.org/0000-0001-7507-6542"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Min Hu","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101135616"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.8724,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9626103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"46","issue":"12","first_page":"11186","last_page":"11199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.7505999803543091,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.7505999803543091,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7452999949455261,"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":0.6997463703155518},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6485289335250854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6480059623718262},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45795026421546936},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4224252998828888},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3989119529724121},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35318589210510254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3504441976547241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997463703155518},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6485289335250854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6480059623718262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45795026421546936},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4224252998828888},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3989119529724121},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35318589210510254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3504441976547241}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3460180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3460180","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39269797","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39269797","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2150593711","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2804452283","https://openalex.org/W2804935296","https://openalex.org/W2964194231","https://openalex.org/W2989611864","https://openalex.org/W3034942609","https://openalex.org/W3094502228","https://openalex.org/W3100341797","https://openalex.org/W3118255477","https://openalex.org/W3153675281","https://openalex.org/W3175759175","https://openalex.org/W3198377975","https://openalex.org/W4206178588","https://openalex.org/W4214926101","https://openalex.org/W4285192809","https://openalex.org/W4302275239","https://openalex.org/W4304086143","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4312575285","https://openalex.org/W4312651322","https://openalex.org/W4312884055","https://openalex.org/W4312960937","https://openalex.org/W4313156423","https://openalex.org/W4313175608","https://openalex.org/W4364302332","https://openalex.org/W4382458283","https://openalex.org/W4386075788","https://openalex.org/W4386076112","https://openalex.org/W4386076397","https://openalex.org/W4386790226","https://openalex.org/W4390872508","https://openalex.org/W4390872642","https://openalex.org/W4390874269","https://openalex.org/W4390874575","https://openalex.org/W4396568157","https://openalex.org/W4399506362","https://openalex.org/W4400315096","https://openalex.org/W4401070841","https://openalex.org/W4402702914","https://openalex.org/W6600983433","https://openalex.org/W6638677478","https://openalex.org/W6759579507","https://openalex.org/W6763468762","https://openalex.org/W6764990469","https://openalex.org/W6779997284","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6802517928","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6811013733","https://openalex.org/W6838639034","https://openalex.org/W6843148291","https://openalex.org/W6844194202","https://openalex.org/W6850625674","https://openalex.org/W6850991314","https://openalex.org/W6851870412","https://openalex.org/W6856398555","https://openalex.org/W6856473036","https://openalex.org/W6857806263"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W1926736923","https://openalex.org/W2942177010"],"abstract_inverted_index":{"Benefiting":[0],"from":[1],"advances":[2],"in":[3,12,28,116,187],"large-scale":[4],"pre-training,":[5],"foundation":[6,95],"models,":[7],"have":[8,129],"demonstrated":[9],"remarkable":[10,168],"capability":[11],"the":[13,81,89,107,123,145,161,171,193],"fields":[14],"of":[15,91,94,110,125,189],"natural":[16],"language":[17],"processing,":[18],"computer":[19],"vision,":[20],"among":[21],"others.":[22],"However,":[23],"to":[24,35,50,100],"achieve":[25],"expert-level":[26],"performance":[27,124,152],"specific":[29],"applications,":[30],"such":[31],"models":[32,49,96],"often":[33],"need":[34],"be":[36],"fine-tuned":[37],"with":[38],"domain-specific":[39],"knowledge.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,62],"focus":[45],"on":[46,73,133],"enabling":[47],"vision-language":[48],"unleash":[51],"more":[52],"potential":[53],"for":[54,79],"visual":[55],"understanding":[56],"tasks":[57],"under":[58,153,160],"few-shot":[59,126],"tuning.":[60,127],"Specifically,":[61],"propose":[63],"a":[64,167],"novel":[65],"adapter,":[66],"dubbed":[67],"as":[68],"lusterAdapter,":[69],"which":[70],"is":[71],"based":[72],"trainable":[74],"multiple":[75],"prototypes":[76],"clustering":[77,117],"algorithm,":[78],"tuning":[80],"CLIP":[82,147,173],"model.":[83],"It":[84],"can":[85],"not":[86],"only":[87],"alleviate":[88],"concern":[90],"catastrophic":[92],"forgetting":[93],"by":[97,174,182],"introducing":[98],"anchors":[99],"inherit":[101],"common":[102,135],"knowledge,":[103],"but":[104],"also":[105,177],"improve":[106],"utilization":[108],"efficiency":[109],"few":[111],"annotated":[112],"samples":[113],"via":[114],"bringing":[115],"and":[118,148,156,176,180,184],"domain":[119],"priors,":[120],"thereby":[121],"improving":[122],"We":[128],"conducted":[130],"extensive":[131],"experiments":[132],"11":[134,194],"classification":[136],"benchmarks.":[137,195],"The":[138],"results":[139],"show":[140],"our":[141,164],"method":[142,165],"significantly":[143],"surpasses":[144,178],"original":[146,172],"achieves":[149],"state-of-the-art":[150],"(SOTA)":[151],"all":[154],"benchmarks":[155],"settings.":[157],"For":[158],"example,":[159],"16-shot":[162],"setting,":[163],"exhibits":[166],"improvement":[169],"over":[170],"19.6%,":[175],"TIP-Adapter":[179],"GraphAdapter":[181],"2.7%":[183],"2.2%,":[185],"respectively,":[186],"terms":[188],"average":[190],"accuracy":[191],"across":[192]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}