{"id":"https://openalex.org/W7166703527","doi":"https://doi.org/10.48550/arxiv.2606.29714","title":"UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction","display_name":"UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166703527","doi":"https://doi.org/10.48550/arxiv.2606.29714"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29714","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.29714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021299658","display_name":"Zhaopeng Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Zhaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104279611","display_name":"B X Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Bingke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139689865","display_name":"Zhaowen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhaowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029271867","display_name":"Guibo Zhu","orcid":"https://orcid.org/0000-0001-8293-3952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Guibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139681636","display_name":"Yingying Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yingying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139692461","display_name":"Ming Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139713161","display_name":"Peng Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139634106","display_name":"Jinqiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8845999836921692,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8845999836921692,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.052000001072883606,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.023499999195337296,"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/boundary","display_name":"Boundary (topology)","score":0.7523999810218811},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7055000066757202},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5813999772071838},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5145000219345093},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47350001335144043},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4016000032424927},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.3952000141143799}],"concepts":[{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.7523999810218811},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247000098228455},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5471000075340271},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4034999907016754},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29714","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.29714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29714","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unified":[0],"visual":[1,101],"anomaly":[2,102,186],"detection":[3,187],"seeks":[4],"to":[5,29,68,150,207],"train":[6],"a":[7,40,93,161],"single":[8],"detector":[9],"that":[10,234],"can":[11],"be":[12],"deployed":[13],"across":[14],"categories,":[15],"domains,":[16],"and":[17,53,73,135,142,184,209,229],"application":[18],"scenarios.":[19],"In":[20],"the":[21,25,62,106,115,152,158,193,199,214,218],"few-shot":[22],"transfer":[23],"regime,":[24],"key":[26],"challenge":[27],"is":[28],"estimate":[30],"an":[31,35,119,136],"episode-specific":[32],"boundary":[33,49,96,175,239],"for":[34,58,82,99,140,174],"unseen":[36,83],"target":[37],"category":[38],"from":[39,50,205],"small":[41],"support":[42],"set.":[43],"Existing":[44],"approaches":[45],"mainly":[46],"infer":[47],"this":[48],"normal-side":[51],"evidence":[52,57,173],"provide":[54],"limited":[55],"abnormal-side":[56],"deployment-specific":[59],"tolerance.":[60],"Within":[61],"normal":[63,116],"side,":[64,160],"they":[65],"often":[66],"struggle":[67],"jointly":[69],"capture":[70],"local":[71],"correspondences":[72],"global":[74],"support-query":[75,130],"relations,":[76],"making":[77],"their":[78],"boundaries":[79],"less":[80],"reliable":[81],"anomalies.":[84],"To":[85],"address":[86],"these":[87],"issues,":[88],"we":[89],"propose":[90],"UniVAD":[91,112,196,204,223],"v2,":[92],"two-sided":[94],"support-conditioned":[95],"construction":[97],"framework":[98,109],"unified":[100],"detection.":[103],"Built":[104],"on":[105,178],"component-patch":[107],"divide-and-conquer":[108],"of":[110,155],"UniVAD,":[111],"v2":[113,197,224],"strengthens":[114],"side":[117],"with":[118,129],"Optimal":[120],"Transport-based":[121],"Relational":[122,143],"Modeling":[123,144],"module":[124,165],"(OTRM),":[125],"which":[126,146],"complements":[127],"retrieval":[128],"matching":[131],"through":[132],"transport-style":[133],"allocation,":[134],"Adaptive":[137],"Coordination":[138],"mechanism":[139],"Retrieval":[141],"(ACRRM),":[145],"estimates":[147],"episode-conditioned":[148],"reliabilities":[149],"fuse":[151],"two":[153],"sources":[154],"evidence.":[156],"On":[157,217],"abnormal":[159,169,235],"Few-Shot":[162],"Abnormal":[163],"Reference":[164],"(FAR)":[166],"converts":[167],"optional":[168],"references":[170,236],"into":[171],"rejection-side":[172],"adjustment.":[176],"Experiments":[177],"six":[179],"datasets":[180],"spanning":[181],"industrial,":[182],"logical,":[183],"medical":[185],"demonstrate":[188],"strong":[189],"cross-domain":[190],"generalization.":[191],"Under":[192],"1N-shot":[194],"protocol,":[195],"improves":[198],"mean":[200],"image-level":[201,227],"AUC":[202,228],"over":[203],"83.0\\%":[206],"84.5\\%,":[208],"further":[210],"reaches":[211],"85.7\\%":[212],"in":[213],"1N+1A-shot":[215],"setting.":[216],"MVTec-AD":[219],"Severity":[220],"Split":[221],"(MVTec-AD-SS),":[222],"achieves":[225],"96.2\\%":[226],"96.9\\%":[230],"pixel-level":[231],"AUC,":[232],"showing":[233],"enable":[237],"controllable":[238],"customization":[240],"without":[241],"retraining.":[242]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}