{"id":"https://openalex.org/W4401857415","doi":"https://doi.org/10.1145/3637528.3671690","title":"Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models","display_name":"Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401857415","doi":"https://doi.org/10.1145/3637528.3671690"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671690","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5038022012","display_name":"Didi Zhu","orcid":"https://orcid.org/0009-0004-6892-5357"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Didi Zhu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031648019","display_name":"Zexi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexi Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102796488","display_name":"Min Zhang","orcid":"https://orcid.org/0009-0001-1289-1571"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049344673","display_name":"Junkun Yuan","orcid":"https://orcid.org/0000-0003-0012-7397"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junkun Yuan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004072676","display_name":"Jiashuo Liu","orcid":"https://orcid.org/0000-0002-9159-1752"},"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":"Jiashuo Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102968689","display_name":"Kun Kuang","orcid":"https://orcid.org/0000-0001-5524-5185"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Kuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056838798","display_name":"Chao Wu","orcid":"https://orcid.org/0000-0003-0885-6869"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5038022012"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.0526,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77890436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4631","last_page":"4640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9966999888420105,"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":0.9890000224113464,"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":0.7010729312896729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4711892604827881},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4127444326877594},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34231385588645935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010729312896729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4711892604827881},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4127444326877594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34231385588645935}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671690","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W3065974826","https://openalex.org/W3159913668","https://openalex.org/W3174770825","https://openalex.org/W3205278400","https://openalex.org/W4205991051","https://openalex.org/W4220771481","https://openalex.org/W4224326479","https://openalex.org/W4226455597","https://openalex.org/W4280510162","https://openalex.org/W4285247752","https://openalex.org/W4291221125","https://openalex.org/W4304084069","https://openalex.org/W4367046615","https://openalex.org/W4367046683","https://openalex.org/W4367046983","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4389518867","https://openalex.org/W4390873355","https://openalex.org/W4390874611","https://openalex.org/W4396758715"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Large-scale":[0],"vision-language":[1],"(V-L)":[2],"models":[3,56,94],"have":[4],"demonstrated":[5],"remarkable":[6],"generalization":[7,27],"capabilities":[8],"for":[9,88,188],"downstream":[10,112],"tasks":[11],"through":[12],"prompt":[13,96,168,182],"tuning.":[14,97],"However,":[15],"the":[16,19,30,38,49,59,64,69,82,90,124,145],"mechanisms":[17],"behind":[18],"learned":[20],"text":[21,139],"representations":[22,73,91,106,142],"are":[23,32],"unknown,":[24],"limiting":[25],"further":[26],"gains,":[28],"and":[29,140,159,162,191],"limitations":[31],"more":[33,116],"severe":[34,117],"when":[35],"faced":[36],"with":[37,111,138,166],"prevalent":[39],"class":[40,119],"imbalances":[41],"seen":[42],"in":[43,48,74,92],"web-sourced":[44],"datasets.":[45],"Recent":[46],"advances":[47],"neural":[50],"collapse":[51,158],"(NC)":[52],"phenomenon":[53],"of":[54,104],"vision-only":[55],"suggest":[57],"that":[58,101,135,143,174],"optimal":[60],"representation":[61],"structure":[62],"is":[63,99,115,164],"simplex":[65,147],"ETF,":[66],"which":[67,114],"paves":[68],"way":[70],"to":[71,85,179],"study":[72],"V-L":[75,93],"models.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,126],"make":[81],"first":[83],"attempt":[84],"use":[86],"NC":[87,102],"examining":[89],"via":[95],"It":[98],"found":[100],"optimality":[103],"text-to-image":[105],"shows":[107],"a":[108,132],"positive":[109],"correlation":[110],"generalizability,":[113],"under":[118],"imbalance":[120],"settings.":[121,193],"To":[122],"improve":[123,180],"representations,":[125],"propose":[127],"Neural-collapse-anchored":[128],"Prompt":[129],"Tuning":[130],"(NPT),":[131],"novel":[133],"method":[134],"learns":[136],"prompts":[137],"image":[141],"satisfy":[144],"same":[146],"Equiangular":[148],"Tight":[149],"Frame":[150],"(ETF).":[151],"NPT":[152,175],"incorporates":[153],"two":[154],"regularization":[155],"terms:":[156],"language-modality":[157],"multi-modality":[160],"isomorphism;":[161],"it":[163],"compatible":[165],"other":[167],"tuning":[169,183],"methods.":[170],"Extensive":[171],"experiments":[172],"show":[173],"can":[176],"consistently":[177],"help":[178],"existing":[181],"techniques":[184],"across":[185],"11":[186],"datasets":[187],"both":[189],"balanced":[190],"imbalanced":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}