{"id":"https://openalex.org/W7169537448","doi":"https://doi.org/10.48550/arxiv.2607.14534","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","display_name":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7169537448","doi":"https://doi.org/10.48550/arxiv.2607.14534"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.14534","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.14534","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":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.2607.14534","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001926325","display_name":"Huong Ninh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ninh, Huong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024157948","display_name":"Chien Thai","orcid":"https://orcid.org/0000-0002-5098-6862"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thai, Chien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042016537","display_name":"Mai Xuan Trang","orcid":"https://orcid.org/0000-0002-9666-0198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trang, Mai Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104229481","display_name":"Vu-Minh Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Vu-Minh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006943571","display_name":"L\u00ea Thanh H\u00e0","orcid":"https://orcid.org/0000-0002-4517-9097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Thanh Ha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124221085","display_name":"Long Van Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Long","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":0.9793000221252441,"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":0.9793000221252441,"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":0.0027000000700354576,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.0015999999595806003,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7217000126838684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6633999943733215},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6417999863624573},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5419999957084656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49889999628067017},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4896000027656555},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4165000021457672},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.40959998965263367}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7217000126838684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6929000020027161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6801999807357788},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6633999943733215},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6417999863624573},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5419999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.14534","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.14534","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2607.14534","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.14534","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.754775881767273,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Industrial":[0],"anomaly":[1,71,157,164,216],"detection":[2,72,165],"aims":[3],"to":[4,47,153],"identify":[5],"and":[6,35,49,56,82,106,142,171,180,192],"localize":[7],"defective":[8],"regions":[9],"without":[10],"relying":[11,131],"on":[12,132,161,194],"exhaustive":[13],"annotations":[14],"of":[15,110,130],"all":[16],"possible":[17],"defect":[18],"types.":[19],"Although":[20],"recent":[21],"unsupervised":[22,70,215],"methods":[23],"have":[24],"achieved":[25],"strong":[26,181],"performance,":[27],"most":[28],"are":[29,147],"primarily":[30],"designed":[31],"for":[32,68],"single-class":[33],"settings":[34],"often":[36],"struggle":[37],"in":[38,189,213],"multi-class":[39,69,214],"scenarios,":[40],"where":[41],"diverse":[42,206],"normal":[43,55,111],"patterns":[44],"may":[45],"lead":[46],"over-generalization":[48],"reduce":[50],"the":[51,143,155],"discriminative":[52],"capability":[53],"between":[54,139],"anomalous":[57],"regions.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,117],"propose":[63],"SwinAD,":[64],"a":[65,75,83,119,133],"reconstruction-based":[66],"framework":[67,123],"that":[73,124,174,200],"leverages":[74],"frozen":[76],"pretrained":[77],"Swin":[78,203],"Transformer":[79],"V2":[80],"encoder":[81,90,140],"feature":[84,120],"diversity-preserving":[85,121],"reconstruction":[86,109,122,127,208],"decoder.":[87],"The":[88,137],"hierarchical":[89,202],"provides":[91],"semantically":[92],"rich":[93],"multi-scale":[94,207],"features,":[95],"while":[96],"stage-wise":[97],"bottleneck":[98],"modules":[99],"with":[100,185,205],"dropout":[101],"prevent":[102],"trivial":[103],"identity":[104],"mapping":[105],"encourage":[107],"robust":[108],"patterns.":[112],"To":[113],"further":[114],"improve":[115,210],"localization,":[116],"introduce":[118],"maintains":[125],"complementary":[126],"hypotheses":[128],"instead":[129],"single":[134],"decoding":[135],"branch.":[136],"discrepancies":[138],"features":[141,146,204],"two":[144],"reconstructed":[145],"then":[148],"aggregated":[149],"across":[150],"multiple":[151],"scales":[152],"produce":[154],"final":[156],"map.":[158],"Experiments":[159],"conducted":[160],"three":[162],"industrial":[163],"benchmarks,":[166],"including":[167],"MVTec":[168,195],"AD,":[169],"VisA,":[170],"Real-IAD,":[172],"demonstrate":[173],"SwinAD":[175],"achieves":[176],"competitive":[177],"image-level":[178],"performance":[179],"pixel-level":[182,190,211],"localization":[183,212],"accuracy,":[184],"particularly":[186],"notable":[187],"improvements":[188],"AP":[191],"1":[193],"AD.":[196],"These":[197],"results":[198],"indicate":[199],"combining":[201],"substantially":[209],"setting.":[217]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-18T00:00:00"}