{"id":"https://openalex.org/W4416798111","doi":"https://doi.org/10.1109/access.2025.3638411","title":"Glocal-HAD: Hybrid Attention Decoder for Reconstruction-Based Vision Anomaly Detection Framework","display_name":"Glocal-HAD: Hybrid Attention Decoder for Reconstruction-Based Vision Anomaly Detection Framework","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416798111","doi":"https://doi.org/10.1109/access.2025.3638411"},"language":null,"primary_location":{"id":"doi:10.1109/access.2025.3638411","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3638411","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.2025.3638411","any_repository_has_fulltext":false},"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":true,"raw_author_name":"Mariam Ishtiaq","raw_affiliation_strings":["Railroad Physical AI Research Department, Korea Railroad Research Institute (KRRI), Uiwang, South Korea"],"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/A5074436414","display_name":"Jong-Un 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"],"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":2,"corresponding_author_ids":["https://openalex.org/A5009942977"],"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":2.4253,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9216831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"208681","last_page":"208695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9810000061988831,"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":0.9810000061988831,"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":0.005400000140070915,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.0012000000569969416,"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":0.704200029373169},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4528999924659729},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4498000144958496},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44859999418258667},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44179999828338623},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43149998784065247},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4169999957084656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.3959999978542328},{"id":"https://openalex.org/keywords/intrusion-detection-system","display_name":"Intrusion detection system","score":0.37709999084472656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144999742507935},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.704200029373169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5271999835968018},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44859999418258667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4169999957084656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2781121602","wikidata":"https://www.wikidata.org/wiki/Q3504403","display_name":"Modular neural network","level":4,"score":0.30649998784065247},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2025.3638411","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3638411","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"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3638411","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3638411","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Industry":[0],"5.0":[1],"has":[2],"garnered":[3],"significant":[4],"research":[5,63,228],"interest":[6],"in":[7],"addressing":[8],"ill-posed":[9],"automation":[10],"challenges,":[11],"such":[12],"as":[13],"vision-based":[14],"anomaly":[15,54,69],"detection":[16,70],"(VAD).":[17],"The":[18,80,175],"heterogeneous":[19],"nature":[20],"of":[21,26,131,138,186],"anomalies":[22],"renders":[23],"the":[24,201,216],"development":[25],"multi-class":[27],"and":[28,57,75,100,116,135,140,150,184,188,197,221,234],"multi-scale":[29],"VAD":[30],"challenging.":[31],"Although":[32],"models":[33,168],"based":[34],"on":[35,191,200],"transformer":[36],"architecture":[37],"have":[38],"delivered":[39],"state-of-the-art":[40],"(SOTA)":[41],"performance,":[42],"they":[43],"struggle":[44],"with":[45,50,106,120,133,169,178],"broader":[46],"context":[47,115,162],"feature":[48,88,98],"fusion":[49],"a":[51,67,91,121,208],"balance":[52,218],"between":[53,219],"detection,":[55],"localization":[56],"computation":[58],"cost.":[59],"To":[60],"fill":[61],"this":[62],"gap,":[64],"we":[65,156,224],"propose":[66,207],"reconstruction-based":[68],"framework":[71],"using":[72,145],"hybrid":[73],"global":[74,114,161,170],"local":[76,127,165],"attention":[77,104,171],"decoder":[78],"(Glocal-HAD).":[79],"proposed":[81,176],"pipeline":[82,177],"uses:":[83],"(i)":[84],"DINOv2":[85],"encoder":[86],"for":[87,96,113,125,159],"extraction,":[89],"(ii)":[90],"regularized":[92],"multi-layer":[93],"perceptron":[94],"(MLP)":[95],"latent":[97],"compression,":[99],"(iii)":[101],"Glocal-HAD.":[102],"Linear":[103],"(LA)":[105],"associative":[107],"key-value":[108],"(KV)":[109],"aggregation":[110],"is":[111],"employed":[112],"masked":[117],"self-attention":[118],"(SA)":[119],"constant":[122],"drop":[123],"rate":[124],"efficient":[126],"context.":[128],"Four":[129],"variants":[130],"HAD":[132],"stacked":[134,179],"interleaved":[136],"settings":[137],"SA":[139],"LA":[141],"layers":[142],"are":[143],"evaluated":[144],"two":[146],"benchmark":[147],"datasets:":[148],"MVTec-AD":[149],"VisA.":[151],"Using":[152],"extensive":[153],"ablation":[154],"experiments,":[155],"conclude":[157],"that":[158],"VAD,":[160],"must":[163],"inform":[164],"refinement,":[166],"since":[167],"first,":[172],"perform":[173],"better.":[174],"Glocal-HAD":[180],"gives":[181],"an":[182,194],"I-AUROC":[183,196],"P-AUROC":[185,198],"99.5%":[187],"98.2%":[189],"respectively,":[190],"MVTec,":[192],"while":[193],"98.5%":[195],"each":[199],"more":[202],"challenging":[203],"VisA":[204],"dataset.":[205],"We":[206],"novel":[209],"performance":[210],"evaluation":[211],"score":[212],"(PES)":[213],"to":[214,231],"evaluate":[215],"model\u2019s":[217],"accuracy":[220],"efficiency.":[222],"Additionally,":[223],"share":[225],"interesting":[226],"open":[227],"problems":[229],"related":[230],"model":[232],"parameterization":[233],"regularization.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-11-28T00:00:00"}