{"id":"https://openalex.org/W7160261058","doi":"https://doi.org/10.1109/access.2026.3689927","title":"De-FuSE\u2014Disentangled Frequency and Semantic Embeddings for Unified Vision Anomaly Detection","display_name":"De-FuSE\u2014Disentangled Frequency and Semantic Embeddings for Unified Vision Anomaly Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160261058","doi":"https://doi.org/10.1109/access.2026.3689927"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3689927","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3689927","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3689927","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009942977","display_name":"Mariam Ishtiaq","orcid":"https://orcid.org/0000-0003-1450-4149"},"institutions":[{"id":"https://openalex.org/I4210161173","display_name":"Korea Railroad Research Institute","ror":"https://ror.org/04gzcxt97","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4210161173","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mariam Ishtiaq","raw_affiliation_strings":["Railroad Physical AI Research Department, Korea Railroad Research Institute (KRRI), Uiwang, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1450-4149","affiliations":[{"raw_affiliation_string":"Railroad Physical AI Research Department, Korea Railroad Research Institute (KRRI), Uiwang, South Korea","institution_ids":["https://openalex.org/I4210161173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103743312","display_name":"JongUn Won","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161173","display_name":"Korea Railroad Research Institute","ror":"https://ror.org/04gzcxt97","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4210161173","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongun Won","raw_affiliation_strings":["Railroad Physical AI Research Department, Korea Railroad Research Institute (KRRI), Uiwang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4702-0960","affiliations":[{"raw_affiliation_string":"Railroad Physical AI Research Department, Korea Railroad Research Institute (KRRI), Uiwang, South Korea","institution_ids":["https://openalex.org/I4210161173"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210161173"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53271617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"69011","last_page":"69023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9685999751091003,"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":0.9685999751091003,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.007899999618530273,"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":0.003100000089034438,"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/anomaly-detection","display_name":"Anomaly detection","score":0.6079999804496765},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5758000016212463},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5414999723434448},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5127999782562256},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44600000977516174},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.37139999866485596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36890000104904175},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.32690000534057617},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.31189998984336853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947999835014343},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5758000016212463},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5414999723434448},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699999988079071},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.27230000495910645},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3689927","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3689927","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0d7eff20dad7452ab539c9778030faec","is_oa":true,"landing_page_url":"https://doaj.org/article/0d7eff20dad7452ab539c9778030faec","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 69011-69023 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3689927","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3689927","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4517957893","display_name":null,"funder_award_id":"PK26312A1","funder_id":"https://openalex.org/F4320322096","funder_display_name":"Korea Railroad Research Institute"}],"funders":[{"id":"https://openalex.org/F4320322096","display_name":"Korea Railroad Research Institute","ror":"https://ror.org/04gzcxt97"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"anomaly":[1,18,27],"detection":[2,28],"(VAD)":[3],"is":[4,46,233],"an":[5,209],"open":[6],"research":[7],"problem":[8],"due":[9],"to":[10,14,31,86,120,158,227],"underlying":[11],"challenges":[12],"pertaining":[13],"cross-functional":[15],"deployment":[16],"and":[17,73,188],"diversity.":[19],"Among":[20],"the":[21,41,77,95,104,113,121,125,149,185,192,200],"key":[22],"solutions":[23],"in":[24,71,148,223],"literature,":[25],"unified":[26,202,229],"(UAD)":[29],"aims":[30],"learn":[32],"a":[33,59,136,142,155,171,219],"single":[34],"generalized":[35],"model":[36,224],"for":[37,63,197],"heterogeneous":[38],"anomalies.":[39,99],"However,":[40],"realization":[42],"of":[43,80,98,194],"this":[44],"scalability":[45],"constrained":[47],"by":[48],"limited":[49],"data":[50],"availability.":[51],"Since":[52],"frozen":[53],"foundation":[54],"models":[55],"like":[56],"DINOv2":[57],"provide":[58],"strong":[60],"semantic":[61,91,106,130],"backbone":[62],"self-supervised":[64],"training,":[65],"they":[66],"have":[67],"been":[68],"readily":[69],"used":[70],"diffusion":[72],"reconstruction-based":[74,83],"UAD.":[75],"But":[76],"stochastic":[78],"nature":[79],"anomalies":[81],"renders":[82],"methods":[84],"susceptible":[85],"identity":[87],"shortcut,":[88],"where":[89],"powerful":[90],"priors":[92,161],"trivially":[93,116],"reconstruct":[94],"input":[96],"regardless":[97],"We":[100],"argue":[101],"that":[102],"decoupling":[103],"invariant":[105],"signal":[107],"from":[108,115,132],"variant":[109],"high-frequency":[110,133],"residuals":[111,134],"prevents":[112],"decoder":[114],"mapping":[117],"anomalous":[118],"regions":[119],"normal":[122],"manifold.":[123],"Therefore,":[124],"proposed":[126],"De-FuSE":[127,204,217],"architecture":[128],"disentangles":[129],"representations":[131],"as":[135,154],"functional":[137],"separation.":[138],"Our":[139],"method":[140],"introduces":[141],"semantic-guided":[143],"cross-frequency":[144],"attention":[145],"(CFA)":[146],"mechanism":[147],"hybrid":[150],"decoder,":[151],"which":[152],"acts":[153],"conditional":[156],"gate":[157],"inject":[159],"frequency":[160,180],"with":[162,178,208],"semantically":[163],"aligned":[164],"queries.We":[165],"further":[166],"enforce":[167],"spectral":[168],"fidelity":[169],"through":[170],"composite":[172],"loss":[173],"function":[174],"combining":[175],"hard-mining":[176],"strategies":[177],"focal":[179],"loss.":[181],"Extensive":[182],"experimentation":[183],"on":[184],"MPDD,":[186],"VisA,":[187],"MVTec-AD":[189],"benchmarks":[190],"demonstrates":[191],"superiority":[193],"our":[195],"approach":[196],"VAD.":[198],"In":[199],"challenging":[201],"setting,":[203],"achieves":[205],"competitive":[206],"accuracy":[207],"efficient":[210],"design.":[211],"With":[212],"just":[213],"59.1M":[214],"trainable":[215],"parameters,":[216],"delivers":[218],"massive":[220],"31.75%":[221],"reduction":[222],"complexity":[225],"compared":[226],"baseline":[228],"frameworks.":[230],"The":[231],"code":[232],"available":[234],"here.":[235]},"counts_by_year":[],"updated_date":"2026-05-13T06:04:23.736269","created_date":"2026-05-06T00:00:00"}