{"id":"https://openalex.org/W4408353597","doi":"https://doi.org/10.1109/icassp49660.2025.10888937","title":"Test-time Alignment-Enhanced Adapter for Vision-Language Models","display_name":"Test-time Alignment-Enhanced Adapter for Vision-Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353597","doi":"https://doi.org/10.1109/icassp49660.2025.10888937"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Baoshun Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoshun Tong","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049156119","display_name":"Kaiyu Song","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyu Song","raw_affiliation_strings":["Sun Yat-Sen University,School of Artificial Intelligence,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Artificial Intelligence,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076868018","display_name":"Hanjiang Lai","orcid":"https://orcid.org/0000-0001-8057-6744"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanjiang Lai","raw_affiliation_strings":["Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9821000099182129,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9789999723434448,"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/adapter","display_name":"Adapter (computing)","score":0.7766442894935608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382577657699585},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5069646835327148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43037623167037964},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17996123433113098}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7766442894935608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382577657699585},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5069646835327148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43037623167037964},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17996123433113098},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"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/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2963091558","https://openalex.org/W2964194231","https://openalex.org/W2982220924","https://openalex.org/W3006487162","https://openalex.org/W3037492894","https://openalex.org/W3175215201","https://openalex.org/W3176693010","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4312310776","https://openalex.org/W4313175608","https://openalex.org/W4385245566","https://openalex.org/W4386075882","https://openalex.org/W4386790226","https://openalex.org/W4388514564","https://openalex.org/W4390190100","https://openalex.org/W4390874140","https://openalex.org/W4393148714","https://openalex.org/W4402774099","https://openalex.org/W6600983433","https://openalex.org/W6638677478","https://openalex.org/W6757817989","https://openalex.org/W6763468762","https://openalex.org/W6764990469","https://openalex.org/W6784333009","https://openalex.org/W6788125050","https://openalex.org/W6791353385","https://openalex.org/W6842574522","https://openalex.org/W6846310912"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2485605994"],"abstract_inverted_index":{"Test-time":[0,56],"adaptation":[1],"with":[2,64,136],"pre-trained":[3,119],"vision-language":[4],"models":[5],"(VLMs)":[6],"has":[7],"attracted":[8],"increasing":[9],"attention":[10],"for":[11],"tackling":[12],"the":[13,19,72,78,96,107,114,127,133],"issue":[14],"of":[15,109,118,124],"distribution":[16,30],"shift":[17,31],"during":[18,71],"test":[20,65,73],"phase.":[21,74],"While":[22],"prior":[23],"methods":[24],"have":[25],"shown":[26],"effectiveness":[27],"in":[28],"addressing":[29],"by":[32,82,121],"adjusting":[33],"classification":[34],"logits,":[35],"they":[36],"are":[37],"not":[38],"optimal":[39],"due":[40],"to":[41,67,86,94],"keeping":[42],"text":[43,69,88],"features":[44,70],"unchanged.":[45],"To":[46],"address":[47],"this":[48],"issue,":[49],"we":[50,91],"introduce":[51],"a":[52],"new":[53],"approach":[54,112],"called":[55],"Alignment-Enhanced":[57],"Adapter":[58],"(TAEA),":[59],"which":[60,104],"trains":[61],"an":[62,84,122,137],"adapter":[63,85],"samples":[66],"adjust":[68],"We":[75],"can":[76],"enhance":[77],"text-to-image":[79],"alignment":[80],"prediction":[81],"utilizing":[83],"adapt":[87],"features.":[89],"Furthermore,":[90],"also":[92],"propose":[93],"adopt":[95],"negative":[97],"cache":[98],"from":[99],"TDA":[100],"as":[101],"enhancement":[102],"module,":[103],"further":[105],"improves":[106],"performance":[108],"TAEA.":[110],"Our":[111],"outperforms":[113],"state-of-the-art":[115],"TTA":[116],"method":[117],"VLMs":[120],"average":[123],"0.75%":[125],"on":[126,132],"out-of-distribution":[128],"benchmark":[129],"and":[130],"2.5%":[131],"cross-domain":[134],"benchmark,":[135],"acceptable":[138],"training":[139],"time.":[140],"Code":[141],"will":[142],"be":[143],"available":[144],"at":[145],"https://github.com/BaoshunWq/clip-TAEA.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}