{"id":"https://openalex.org/W4413147514","doi":"https://doi.org/10.1109/cvpr52734.2025.01435","title":"Overcoming Shortcut Problem in VLM for Robust Out-of-Distribution Detection","display_name":"Overcoming Shortcut Problem in VLM for Robust Out-of-Distribution Detection","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147514","doi":"https://doi.org/10.1109/cvpr52734.2025.01435"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":"https://openalex.org/A5049414129","display_name":"Zhuo Xu","orcid":"https://orcid.org/0009-0000-1530-8938"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Xu","raw_affiliation_strings":["Huazhong University of Science and Technology,National Key Lab of Multi-Spectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,National Key Lab of Multi-Spectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094302520","display_name":"Xiang Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xiang","raw_affiliation_strings":["Huazhong University of Science and Technology,National Key Lab of Multi-Spectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,National Key Lab of Multi-Spectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074593788","display_name":"Yifan Liang","orcid":"https://orcid.org/0000-0002-7161-2157"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Liang","raw_affiliation_strings":["Huazhong University of Science and Technology,National Key Lab of Multi-Spectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,National Key Lab of Multi-Spectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15402","last_page":"15412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9904000163078308,"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/T11324","display_name":"Spectroscopy Techniques in Biomedical and Chemical Research","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6259917616844177},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4572564661502838},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41162192821502686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18554720282554626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6259917616844177},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4572564661502838},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41162192821502686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18554720282554626},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs),":[2],"such":[3],"as":[4,52,105],"CLIP,":[5],"have":[6],"shown":[7],"remarkable":[8],"capabilities":[9],"in":[10,25,69,159,166],"downstream":[11],"tasks.":[12],"However,":[13],"the":[14,20,23,61,65,93,111,118,129],"coupling":[15],"of":[16,67,100,146],"semantic":[17],"information":[18],"between":[19],"foreground":[21],"and":[22,71,78,88,91,169,175],"background":[24,43,76,103,114,133,147],"images":[26,85,148],"leads":[27],"to":[28,49,95,116],"significant":[29],"shortcut":[30],"issues":[31],"that":[32],"adversely":[33],"affect":[34],"out-of-distribution":[35],"(OOD)":[36],"detection":[37],"abilities.":[38],"When":[39],"confronted":[40],"with":[41,149],"a":[42,97,137],"OOD":[44,62,102,139],"sample,":[45],"VLMs":[46,70],"are":[47,178],"prone":[48],"misidentifying":[50],"it":[51],"in-distribution":[53],"(ID)":[54],"data.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,135],"analyze":[60],"problem":[63],"from":[64,113],"perspective":[66],"shortcuts":[68],"propose":[72],"OSPCoOp":[73],"which":[74,143],"includes":[75],"decoupling":[77,115],"mask-guided":[79],"region":[80],"regularization.":[81],"We":[82,108],"first":[83],"decouple":[84],"into":[86],"ID-relevant":[87,151],"ID-irrelevant":[89,125],"regions":[90,152],"utilize":[92],"latter":[94],"generate":[96],"large":[98],"number":[99],"augmented":[101],"samples":[104],"pseudo-OOD":[106],"supervision.":[107],"then":[109],"use":[110],"masks":[112],"adjust":[117],"model\u2019s":[119,130],"attention,":[120],"minimizing":[121],"its":[122],"focus":[123],"on":[124],"regions.":[126],"To":[127],"assess":[128],"robustness":[131],"against":[132],"interference,":[134],"introduce":[136],"new":[138],"evaluation":[140],"dataset,":[141],"ImageNet-Bg,":[142],"solely":[144],"consists":[145],"all":[150],"removed.":[153],"Our":[154],"method":[155],"demonstrates":[156],"exceptional":[157],"performance":[158],"few-shot":[160],"scenarios,":[161],"achieving":[162],"strong":[163],"results":[164],"even":[165],"one-shot":[167],"setting,":[168],"outperforms":[170],"existing":[171],"methods.":[172],"The":[173],"code":[174],"proposed":[176],"ImageNet-Bg":[177],"available":[179],"at":[180],"https://github.com/HAIV-Lab/OSPCoOp_Imagenet-bg.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}