{"id":"https://openalex.org/W4412837107","doi":"https://doi.org/10.1109/tpami.2025.3594894","title":"Decouple Before Align: Visual Disentanglement Enhances Prompt Tuning","display_name":"Decouple Before Align: Visual Disentanglement Enhances Prompt Tuning","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4412837107","doi":"https://doi.org/10.1109/tpami.2025.3594894","pmid":"https://pubmed.ncbi.nlm.nih.gov/40748795"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3594894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3594894","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5100412178","display_name":"Fei Zhang","orcid":"https://orcid.org/0000-0002-4488-8692"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Zhang","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-6618-269X","affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210099312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091518967","display_name":"Tianfei Zhou","orcid":"https://orcid.org/0000-0001-5475-1473"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianfei Zhou","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China","Beijing Institute of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-5475-1473","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922412","display_name":"Jiangchao Yao","orcid":"https://orcid.org/0000-0001-6115-5194"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangchao Yao","raw_affiliation_strings":["Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6115-5194","affiliations":[{"raw_affiliation_string":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210099312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342828","display_name":"Ya Zhang","orcid":"https://orcid.org/0000-0002-5390-9053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5390-9053","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021751767","display_name":"Ivor W. Tsang","orcid":"https://orcid.org/0000-0001-8095-4637"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ivor W. Tsang","raw_affiliation_strings":["A* A*STAR, Centre for Frontier AI Research, Singapore","A*STAR Centre for Frontier AI Research, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8095-4637","affiliations":[{"raw_affiliation_string":"A* A*STAR, Centre for Frontier AI Research, Singapore","institution_ids":["https://openalex.org/I4210161496"]},{"raw_affiliation_string":"A*STAR Centre for Frontier AI Research, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645710","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0002-8623-1111"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3196-2347","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7705,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71931053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"47","issue":"11","first_page":"10619","last_page":"10632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10427","display_name":"Visual perception and processing mechanisms","score":0.3483999967575073,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10427","display_name":"Visual perception and processing mechanisms","score":0.3483999967575073,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.62773597240448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5847971439361572},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4731368124485016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33910441398620605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.62773597240448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5847971439361572},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4731368124485016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33910441398620605}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3594894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3594894","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40748795","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40748795","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G182816160","display_name":null,"funder_award_id":"62306178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2204858012","display_name":null,"funder_award_id":"L252036","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G6360183275","display_name":null,"funder_award_id":"22DZ2229005","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1920259731","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2128059732","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2295107390","https://openalex.org/W2533598788","https://openalex.org/W2798715809","https://openalex.org/W2896457183","https://openalex.org/W2962858109","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3113682753","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4206648492","https://openalex.org/W4224952733","https://openalex.org/W4226058394","https://openalex.org/W4307844773","https://openalex.org/W4312310776","https://openalex.org/W4312436160","https://openalex.org/W4312651322","https://openalex.org/W4313153210","https://openalex.org/W4321194933","https://openalex.org/W4386065763","https://openalex.org/W4386065874","https://openalex.org/W4386071547","https://openalex.org/W4386071798","https://openalex.org/W4386113259","https://openalex.org/W4390872773","https://openalex.org/W4390873481","https://openalex.org/W4390873714","https://openalex.org/W4390873795","https://openalex.org/W4390874575","https://openalex.org/W4402716166","https://openalex.org/W4402753899","https://openalex.org/W4402783842"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"Prompt":[0],"tuning":[1],"(PT),":[2],"as":[3],"an":[4,74,80],"emerging":[5],"resource-efficient":[6],"fine-tuning":[7],"paradigm,":[8],"has":[9],"showcased":[10],"remarkable":[11],"effectiveness":[12],"in":[13,31,54],"improving":[14],"the":[15,34,42,55,59,65,90,94,115,120,127,133,144,148,156,161],"task-specific":[16],"transferability":[17],"of":[18,108,163,175],"vision-language":[19],"models.":[20],"This":[21],"paper":[22],"delves":[23],"into":[24,93],"a":[25,138],"previously":[26],"overlooked":[27],"information":[28],"asymmetry":[29],"issue":[30],"PT,":[32],"where":[33],"visual":[35,91,102,134,139,150],"modality":[36,92],"mostly":[37],"conveys":[38],"more":[39],"context":[40,66],"than":[41],"object-oriented":[43],"textual":[44],"modality.":[45],"Correspondingly,":[46],"coarsely":[47],"aligning":[48],"these":[49,109],"two":[50],"modalities":[51],"could":[52],"result":[53],"biased":[56],"attention,":[57],"driving":[58],"model":[60],"to":[61,87],"merely":[62],"focus":[63],"on":[64,79,155],"area.":[67],"To":[68,130],"address":[69],"this,":[70],"we":[71,85,136],"propose":[72,86,137],"DAPT,":[73],"effective":[75],"PT":[76],"framework":[77],"based":[78],"intuitive":[81],"decouple-before-align":[82],"concept.":[83],"First,":[84],"explicitly":[88],"decouple":[89],"foreground":[95,117],"and":[96,105,119,171],"background":[97,122],"representation":[98,151],"via":[99],"exploiting":[100],"coarse-and-fine":[101],"segmenting":[103],"cues,":[104],"then":[106],"both":[107],"decoupled":[110],"patterns":[111],"are":[112],"aligned":[113],"with":[114],"original":[116,149],"texts":[118],"hand-crafted":[121],"classes,":[123],"thereby":[124],"symmetrically":[125],"strengthening":[126],"modal":[128],"alignment.":[129],"further":[131],"enhance":[132],"concentration,":[135],"pull-push":[140],"regularization":[141],"tailored":[142],"for":[143],"foreground-background":[145],"patterns,":[146],"directing":[147],"towards":[152],"unbiased":[153],"attention":[154],"region-of-interest":[157],"object.":[158],"We":[159],"demonstrate":[160],"power":[162],"architecture-free":[164],"DAPT":[165],"through":[166],"few-shot":[167],"learning,":[168,173],"base-to-novel":[169],"generalization,":[170],"data-efficient":[172],"all":[174],"which":[176],"yield":[177],"superior":[178],"performance":[179],"across":[180],"prevailing":[181],"benchmarks.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}