{"id":"https://openalex.org/W4407123929","doi":"https://doi.org/10.1109/wacv61042.2026.00269","title":"Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation","display_name":"Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4407123929","doi":"https://doi.org/10.1109/wacv61042.2026.00269"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.00662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008792199","display_name":"Yimu Wang","orcid":"https://orcid.org/0000-0003-4255-9104"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yimu Wang","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116142563","display_name":"Evelien Riddell","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evelien Riddell","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108376200","display_name":"Adrian Chow","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Adrian Chow","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081670169","display_name":"Sean Sedwards","orcid":"https://orcid.org/0000-0002-2903-0823"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sean Sedwards","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066916130","display_name":"Krzysztof Czarnecki","orcid":"https://orcid.org/0000-0003-1642-1101"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Krzysztof Czarnecki","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00666846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2741","last_page":"2751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9710999727249146,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9710999727249146,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9670000076293945,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9624000191688538,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8399736881256104},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7687579393386841},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6000919938087463},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5645160675048828},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5478205680847168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5156673192977905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082637667655945},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.506060779094696},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4792040288448334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32068854570388794},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18558207154273987},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08349370956420898},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.0638367235660553}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8399736881256104},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7687579393386841},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6000919938087463},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5645160675048828},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5478205680847168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5156673192977905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082637667655945},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.506060779094696},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4792040288448334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32068854570388794},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18558207154273987},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08349370956420898},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0638367235660553},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.00662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00662","pdf_url":"https://arxiv.org/pdf/2502.00662","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.00662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.00662","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.00662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00662","pdf_url":"https://arxiv.org/pdf/2502.00662","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4407123929.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W627697492"],"abstract_inverted_index":{"Existing":[0],"vision-language":[1],"model":[2],"(VLM)-based":[3],"methods":[4],"for":[5],"out-of-distribution":[6],"(OOD)":[7],"detection":[8,80,182],"typically":[9],"rely":[10],"on":[11,122,131],"similarity":[12,43],"scores":[13],"between":[14,26,91],"input":[15],"images":[16],"and":[17,28,70,93,108,117,146,154,168],"in-distribution":[18],"(ID)":[19],"text":[20,29,46,65,129],"prototypes.":[21,47,66],"However,":[22],"the":[23,50,89,123,132,140],"modality":[24,54,141],"gap":[25,90,142],"image":[27,60,92,135],"often":[30],"results":[31],"in":[32],"high":[33,42],"false":[34],"positive":[35],"rates,":[36],"as":[37],"OOD":[38,79,161,181],"samples":[39],"can":[40],"exhibit":[41],"to":[44],"ID":[45,59,64,128],"To":[48,86],"mitigate":[49],"impact":[51],"of":[52],"this":[53,75],"gap,":[55],"we":[56,95,157],"propose":[57],"incorporating":[58],"prototypes":[61,130],"along":[62],"with":[63],"We":[67],"present":[68],"theoretical":[69,153],"empirical":[71,155],"evidence":[72],"indicating":[73],"that":[74,175],"approach":[76],"enhances":[77,114],"VLM-based":[78,180],"performance":[81],"without":[82],"any":[83],"additional":[84],"training.":[85],"further":[87],"reduce":[88],"text,":[94],"introduce":[96,158],"a":[97,159],"novel":[98,160],"few-shot":[99],"tuning":[100],"framework,":[101],"suPreMe,":[102],"comprising":[103],"biased":[104],"prompt":[105],"generation":[106],"(BPG)":[107],"image-text":[109,115],"consistency":[110],"(ITC)":[111],"modules.":[112],"BPG":[113],"fusion":[116],"improves":[118],"generalization":[119],"(prevents":[120],"overfitting":[121],"training":[124],"data)":[125],"by":[126,143,151],"conditioning":[127],"Gaussian-based":[133],"estimated":[134],"domain":[136],"bias;":[137],"ITC":[138],"reduces":[139],"minimizing":[144],"intra-":[145],"inter-modal":[147],"distances.":[148],"Moreover,":[149],"inspired":[150],"our":[152],"findings,":[156],"score":[162],"S<inf":[163],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[164],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">GMP</inf>,":[165],"leveraging":[166],"uni-":[167],"cross-modal":[169],"similarities.":[170],"Finally,":[171],"extensive":[172],"experiments":[173],"demonstrate":[174],"suPreMe":[176],"consistently":[177],"outperforms":[178],"existing":[179],"methods.":[183]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-10-10T00:00:00"}