{"id":"https://openalex.org/W4416251358","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227756","title":"Debiased Prompt Tuning for Vision-Language Models without Annotations","display_name":"Debiased Prompt Tuning for Vision-Language Models without Annotations","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251358","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227756"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5011513147","display_name":"Chaoquan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoquan Jiang","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100314060","display_name":"Yunfan Yang","orcid":"https://orcid.org/0000-0002-4307-5569"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfan Yang","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675124","display_name":"Rui Hu","orcid":"https://orcid.org/0009-0001-7891-1950"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Hu","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023834030","display_name":"Jitao Sang","orcid":"https://orcid.org/0000-0002-0699-3205"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Sang","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer and Information Technology & Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.30333008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8511999845504761,"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":0.8511999845504761,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.052299998700618744,"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/T10028","display_name":"Topic Modeling","score":0.01209999993443489,"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/spurious-relationship","display_name":"Spurious relationship","score":0.9828000068664551},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8238000273704529},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6570000052452087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36550000309944153},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3212999999523163}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.9828000068664551},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8238000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494000196456909},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425000190734863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":22,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2788633781","https://openalex.org/W2962858109","https://openalex.org/W2967177252","https://openalex.org/W3011721937","https://openalex.org/W3016970897","https://openalex.org/W3120485916","https://openalex.org/W3190208102","https://openalex.org/W3198377975","https://openalex.org/W4304142266","https://openalex.org/W4312310776","https://openalex.org/W4312436160","https://openalex.org/W4312678124","https://openalex.org/W4312747482","https://openalex.org/W4312901583","https://openalex.org/W4312910992","https://openalex.org/W4382240281","https://openalex.org/W4385893817","https://openalex.org/W4386065763","https://openalex.org/W4386065884","https://openalex.org/W4402727054","https://openalex.org/W4404783412"],"related_works":[],"abstract_inverted_index":{"Prompt":[0],"tuning":[1,97],"of":[2,32,76,95,105,115,125,144],"Vision-Language":[3],"Models":[4],"(VLMs)":[5],"such":[6],"as":[7],"CLIP,":[8],"has":[9],"demonstrated":[10],"the":[11,30,36,47,53,72,83,92,110,123,141,155,165,170,174],"ability":[12,114],"to":[13,16,52,70,117,138],"rapidly":[14],"adapt":[15],"various":[17],"downstream":[18],"tasks.":[19],"However,":[20],"recent":[21],"studies":[22],"indicate":[23],"that":[24,150],"tuned":[25],"VLMs":[26,99,116],"may":[27,50],"suffer":[28],"from":[29],"problem":[31],"spurious":[33,40,65,73,106,119],"correlations,":[34],"where":[35],"model":[37,54],"relies":[38],"on":[39,102,158],"features":[41],"(e.g.":[42],"background":[43],"and":[44,161,173],"gender)":[45],"in":[46,58,82,98],"data.":[48,60],"This":[49],"lead":[51],"having":[55],"worse":[56],"robustness":[57,94,167],"out-of-distribution":[59],"Standard":[61],"methods":[62],"for":[63],"eliminating":[64],"correlation":[66],"typically":[67],"require":[68],"us":[69],"know":[71],"attribute":[74,131],"labels":[75],"each":[77],"sample,":[78],"which":[79],"is":[80],"hard":[81],"real":[84],"world.":[85],"In":[86],"this":[87],"work,":[88],"we":[89,133],"explore":[90],"improving":[91],"group":[93],"prompt":[96],"without":[100],"relying":[101],"manual":[103,126],"annotation":[104],"features.":[107],"We":[108],"leverage":[109],"zero-shot":[111],"image":[112],"recognition":[113],"identify":[118],"features,":[120],"thus":[121],"avoiding":[122],"cost":[124],"annotation.":[127],"By":[128],"leveraging":[129],"pseudo-spurious":[130],"annotations,":[132],"further":[134],"propose":[135],"a":[136],"method":[137],"automatically":[139],"adjust":[140],"training":[142],"weights":[143],"different":[145],"groups.":[146],"Extensive":[147],"experiments":[148],"show":[149],"our":[151],"approach":[152],"efficiently":[153],"improves":[154],"worst-group":[156,171],"accuracy":[157,172],"CelebA,":[159],"Waterbirds,":[160],"MetaShift":[162],"datasets,":[163],"achieving":[164],"best":[166],"gap":[168],"between":[169],"overall":[175],"accuracy.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}