{"id":"https://openalex.org/W7166886395","doi":"https://doi.org/10.1109/tip.2026.3706961","title":"Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment","display_name":"Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166886395","doi":"https://doi.org/10.1109/tip.2026.3706961","pmid":"https://pubmed.ncbi.nlm.nih.gov/42384518"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3706961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3706961","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","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/A5090034491","display_name":"Shanshan Wang","orcid":"https://orcid.org/0000-0002-3824-687X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Wang","raw_affiliation_strings":["National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3824-687X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139777718","display_name":"ALuSi","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ALuSi","raw_affiliation_strings":["National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-7295-5960","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034737032","display_name":"Xun Yang","orcid":"https://orcid.org/0000-0003-0201-1638"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Yang","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0201-1638","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042680345","display_name":"Pichao Wang","orcid":"https://orcid.org/0000-0002-1430-0237"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pichao Wang","raw_affiliation_strings":["NVIDIA Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1430-0237","affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755853","display_name":"Ke Xu","orcid":"https://orcid.org/0000-0001-6266-4257"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Xu","raw_affiliation_strings":["National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6266-4257","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028634381","display_name":"Xingyi Zhang","orcid":"https://orcid.org/0000-0002-5052-000X"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyi Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-5052-000X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I1327237609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.85842531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"7428","last_page":"7443"},"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":0.3248000144958496,"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":0.3248000144958496,"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":0.25119999051094055,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.04910000041127205,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.43560001254081726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41780000925064087},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.40059998631477356},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3727000057697296},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3174000084400177},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.29760000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5658000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5471000075340271},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47429999709129333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.43560001254081726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3727000057697296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31869998574256897},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3706961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3706961","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42384518","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42384518","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G354547891","display_name":null,"funder_award_id":"62577001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Test-time":[0],"adaptation":[1,164,181,216],"(TTA)":[2],"has":[3],"emerged":[4],"as":[5,208],"a":[6,80,154,167,174],"key":[7],"strategy":[8],"to":[9,37,45,153],"enhance":[10],"vision-language":[11],"models":[12],"(VLMs)":[13],"under":[14],"real-world":[15],"distribution":[16],"changes.":[17],"However,":[18],"existing":[19],"methods":[20],"always":[21],"face":[22],"two":[23,71],"problems:":[24],"1)":[25],"The":[26],"fundamental":[27],"trade-off":[28],"dilemma:":[29],"parameter-free":[30],"TTA":[31,61],"retains":[32],"inference":[33],"efficiency":[34],"but":[35],"fails":[36],"correct":[38],"modality":[39,86],"misalignment,":[40],"while":[41],"prompt":[42],"tuning":[43],"adapts":[44],"shifts,":[46],"incurs":[47],"high":[48],"computational":[49],"costs,":[50],"and":[51,88,112,173,200],"lacks":[52],"knowledge":[53,165],"retention.":[54],"2)":[55],"Discriminative":[56],"collapse":[57],"also":[58],"exists":[59],"in":[60,137],"when":[62],"faced":[63],"with":[64,130],"fine-grained":[65,138,199],"downstream":[66],"tasks.":[67,139],"To":[68],"alleviate":[69],"these":[70],"bottlenecks,":[72],"we":[73,92,116,142],"introduce":[74,93,143],"Style-aware":[75,94],"Contrastive":[76,119],"Test-Time":[77],"Adaptation":[78,96,120],"(SCTTA),":[79],"novel":[81],"framework":[82],"that":[83,191],"jointly":[84],"addresses":[85],"misalignment":[87],"discriminative":[89,177],"collapse.":[90],"Firstly,":[91],"Embedding":[95],"(SEA),":[97],"which":[98,122,147],"dynamically":[99],"refines":[100],"text":[101],"embeddings":[102],"by":[103,126],"incorporating":[104],"domain-specific":[105],"style":[106],"attributes,":[107],"improving":[108],"alignment":[109],"between":[110],"visual":[111],"textual":[113],"modalities.":[114],"Secondly,":[115],"propose":[117],"Fine-grained":[118],"(FCA),":[121],"enhances":[123],"feature":[124,135],"separation":[125],"enforcing":[127],"contrastive":[128],"learning":[129],"adaptive":[131],"prototypes,":[132],"reducing":[133],"inter-class":[134],"overlap":[136],"In":[140],"addition,":[141],"Dual-Cache":[144],"Model":[145],"(DCM),":[146],"extends":[148],"prior":[149],"unimodal":[150],"cache":[151,156],"model":[152],"multimodal":[155],"for":[157,197],"the":[158],"first":[159],"time.":[160],"Eventually,":[161],"it":[162],"accumulates":[163],"through":[166],"visual-cache":[168],"(capturing":[169],"evolving":[170],"domain":[171],"styles)":[172],"textual-cache":[175],"(retaining":[176],"semantics),":[178],"enabling":[179],"long-term":[180],"without":[182],"additional":[183],"overhead.":[184],"Extensive":[185],"experiments":[186],"on":[187],"15":[188],"datasets":[189],"demonstrate":[190],"our":[192],"approach":[193],"achieves":[194],"state-of-the-art":[195],"performance":[196],"both":[198],"out-of-distribution":[201],"dataset":[202],"benchmarks.":[203],"Furthermore,":[204],"SCTTA":[205],"continuously":[206],"improves":[207],"more":[209],"test":[210],"samples":[211],"accumulate,":[212],"validating":[213],"its":[214],"sustainable":[215],"capacity.":[217],"Our":[218],"code":[219],"is":[220],"available":[221],"at":[222],"https://github.com/alusi123/SCTTA.":[223]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-02T00:00:00"}