{"id":"https://openalex.org/W7160252973","doi":"https://doi.org/10.1109/wacv61042.2026.00243","title":"PVeRA: Probabilistic Vector-Based Random Matrix Adaptation","display_name":"PVeRA: Probabilistic Vector-Based Random Matrix Adaptation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160252973","doi":"https://doi.org/10.1109/wacv61042.2026.00243"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5092362794","display_name":"Leo Fillioux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Leo Fillioux","raw_affiliation_strings":["Université Paris-Saclay,MICS Laboratory, CentraleSupélec"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032685263","display_name":"Enzo Ferrante","orcid":"https://orcid.org/0000-0002-8500-788X"},"institutions":[{"id":"https://openalex.org/I24354313","display_name":"Universidad de Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Enzo Ferrante","raw_affiliation_strings":["Universidad de Buenos Aires,Institute of Computer Sciences, CONICET"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Buenos Aires,Institute of Computer Sciences, CONICET","institution_ids":["https://openalex.org/I24354313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129493934","display_name":"Paul-Henry Courn\u00e8de","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paul-Henry Courn\u00e8de","raw_affiliation_strings":["Université Paris-Saclay,MICS Laboratory, CentraleSupélec"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106466395","display_name":"Maria Vakalopoulou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maria Vakalopoulou","raw_affiliation_strings":["Université Paris-Saclay,MICS Laboratory, CentraleSupélec"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064662363","display_name":"Stergios Christodoulidis","orcid":"https://orcid.org/0000-0002-8773-1070"},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stergios Christodoulidis","raw_affiliation_strings":["Université Paris-Saclay,MICS Laboratory, CentraleSupélec"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay,MICS Laboratory, CentraleSupélec","institution_ids":["https://openalex.org/I4210107720"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68631903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2465","last_page":"2474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0608999989926815,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0608999989926815,"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/T10057","display_name":"Face and Expression Recognition","score":0.03539999946951866,"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/T12303","display_name":"Tensor decomposition and applications","score":0.03310000151395798,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5313000082969666},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.34200000762939453},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.30059999227523804},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2773999869823456},{"id":"https://openalex.org/keywords/random-noise","display_name":"Random noise","score":0.2759000062942505},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.2689000070095062}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5235000252723694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38269999623298645},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":26,"referenced_works":["https://openalex.org/W1567512734","https://openalex.org/W1977295328","https://openalex.org/W2001610032","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2111051539","https://openalex.org/W2115579991","https://openalex.org/W2115733720","https://openalex.org/W2134557905","https://openalex.org/W2254249950","https://openalex.org/W2533598788","https://openalex.org/W2561715562","https://openalex.org/W2592962403","https://openalex.org/W2806857275","https://openalex.org/W2964194231","https://openalex.org/W2984006054","https://openalex.org/W3168433561","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4312651322","https://openalex.org/W4372266552","https://openalex.org/W4386065763","https://openalex.org/W4390871707","https://openalex.org/W4390874575","https://openalex.org/W4415798891","https://openalex.org/W7133219196"],"related_works":[],"abstract_inverted_index":{"Large":[0],"foundation":[1],"models":[2,24,51,181],"have":[3],"emerged":[4],"in":[5,98,134,145],"the":[6,79,91,124,129,146,164],"last":[7],"years":[8],"and":[9,28,35,60,82,148,156,167,174,184],"are":[10,32],"pushing":[11],"performance":[12],"boundaries":[13],"for":[14,150,179],"a":[15,40,76,103,120,135],"variety":[16],"of":[17,58,78,105,123,132],"tasks.":[18,89],"Training":[19],"or":[20],"even":[21],"finetuning":[22],"such":[23,50],"demands":[25],"vast":[26],"datasets":[27],"computational":[29],"resources,":[30],"which":[31,127],"often":[33],"scarce":[34],"costly.":[36],"Adaptation":[37],"methods":[38],"provide":[39],"computationally":[41],"efficient":[42],"solution":[43],"to":[44,52,71,96],"address":[45],"these":[46,85],"limitations":[47],"by":[48,66,101],"allowing":[49],"be":[53],"finetuned":[54],"on":[55,87,163],"small":[56],"amounts":[57],"data":[59],"computing":[61],"power.":[62],"This":[63,138],"is":[64,188],"achieved":[65],"appending":[67],"new":[68],"trainable":[69,80],"modules":[70,86],"frozen":[72,106],"backbones":[73],"with":[74,170,182],"only":[75,84],"fraction":[77],"parameters":[81],"fitting":[83],"novel":[88],"Recently,":[90],"VeRA":[92,125,133,173],"adapter":[93],"was":[94,161],"shown":[95],"excel":[97],"parameter-efficient":[99],"adaptations":[100],"utilizing":[102],"pair":[104],"random":[107],"low-rank":[108,130],"matrices":[109,131],"shared":[110],"across":[111],"all":[112,186],"layers.":[113],"In":[114],"this":[115],"paper,":[116],"we":[117],"propose":[118],"PVeRA,":[119],"probabilistic":[121,136],"version":[122],"adapter,":[126],"modifies":[128],"manner.":[137],"modification":[139],"naturally":[140],"allows":[141,149],"handling":[142],"inherent":[143],"ambiguities":[144],"input":[147],"different":[151],"sampling":[152],"configurations":[153],"during":[154],"training":[155,180],"testing.":[157],"A":[158],"comprehensive":[159],"evaluation":[160],"performed":[162],"VTAB-1k":[165],"benchmark":[166],"seven":[168],"adapters,":[169],"PVeRA":[171,183],"outperforming":[172],"other":[175],"adapters.":[176],"Our":[177],"code":[178],"benchmarking":[185],"adapters":[187],"available":[189],"here.":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}