{"id":"https://openalex.org/W4417098585","doi":"https://doi.org/10.1109/iccv51701.2025.00220","title":"Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models","display_name":"Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417098585","doi":"https://doi.org/10.1109/iccv51701.2025.00220"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01225","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100443896","display_name":"Xinyu Chen","orcid":"https://orcid.org/0000-0002-2245-376X"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Chen","raw_affiliation_strings":["Shanghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050335025","display_name":"Haotian Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Zhai","raw_affiliation_strings":["Beijing University of Chemical Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440826","display_name":"Can Zhang","orcid":"https://orcid.org/0000-0001-9530-5218"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Zhang","raw_affiliation_strings":["Beijing University of Chemical Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103232609","display_name":"Xiupeng Shi","orcid":"https://orcid.org/0000-0003-4930-6193"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiupeng Shi","raw_affiliation_strings":["Shanghai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101737630","display_name":"Ruirui Li","orcid":"https://orcid.org/0000-0002-8014-7170"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruirui Li","raw_affiliation_strings":["Beijing University of Chemical Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology","institution_ids":["https://openalex.org/I75390827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2281","last_page":"2291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9083999991416931,"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":0.9083999991416931,"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":0.03460000082850456,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01899999938905239,"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/initialization","display_name":"Initialization","score":0.6830000281333923},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5680000185966492},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5414999723434448},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4593000113964081},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4542999863624573},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.3953000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825999855995178},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6830000281333923},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4697999954223633},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2776987467","wikidata":"https://www.wikidata.org/wiki/Q5165073","display_name":"Content adaptation","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01225","pdf_url":"https://arxiv.org/pdf/2508.01225","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.01225","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01225","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_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.01225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01225","pdf_url":"https://arxiv.org/pdf/2508.01225","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"zero-shot":[1],"setting,":[2],"test-time":[3],"adaptation":[4],"adjusts":[5],"pre-trained":[6],"models":[7],"using":[8,118],"unlabeled":[9],"data":[10],"from":[11],"the":[12,50,148],"test":[13,20],"phase":[14],"to":[15,31,106],"enhance":[16],"performance":[17,67],"on":[18,27,72],"unknown":[19],"distributions.":[21,58],"Existing":[22],"cache-enhanced":[23,66],"TTA":[24],"methods":[25],"rely":[26],"a":[28,62,77,112,125],"low-entropy":[29,41,95],"criterion":[30],"select":[32],"samples":[33,42],"for":[34,90,100,115],"prototype":[35,92,129,135],"construction,":[36],"assuming":[37],"intra-class":[38,57,69,109],"compactness.":[39,70],"However,":[40],"may":[43,53],"be":[44],"unreliable":[45],"under":[46],"distribution":[47],"shifts,":[48],"and":[49,68,103,111,131,139,151],"resulting":[51],"prototypes":[52],"not":[54],"ensure":[55],"compact":[56,108],"This":[59],"study":[60],"identifies":[61],"positive":[63],"correlation":[64],"between":[65],"Based":[71],"this":[73],"observation,":[74],"we":[75],"propose":[76],"Multi-Cache":[78],"enhanced":[79],"Prototype-based":[80],"Test-Time":[81],"Adaptation":[82],"(MCP)":[83],"featuring":[84],"three":[85],"caches:":[86],"an":[87,97],"entropy":[88],"cache":[89,99,114],"initializing":[91],"representations":[93],"with":[94],"samples,":[96],"align":[98],"integrating":[101],"visual":[102],"textual":[104],"information":[105],"achieve":[107,153],"distributions,":[110],"negative":[113],"prediction":[116],"calibration":[117],"high-entropy":[119],"samples.":[120],"We":[121],"further":[122],"developed":[123],"MCP++,":[124],"framework":[126,152],"incorporating":[127],"cross-modal":[128],"alignment":[130],"residual":[132,136],"learning,":[133],"introducing":[134],"fine-tuning.":[137],"Comparative":[138],"ablation":[140],"experiments":[141],"across":[142],"15":[143],"downstream":[144],"tasks":[145],"demonstrate":[146],"that":[147],"proposed":[149],"method":[150],"state-of-the-art":[154],"generalization":[155],"performance.":[156],"Project":[157],"Page":[158],"available":[159],"at:":[160],"https://zhaihaotian.github.io/MCP-ICCV25/":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}