{"id":"https://openalex.org/W7225653349","doi":"https://doi.org/10.1007/s44163-026-02671-5","title":"Pyramidal inhibitory lightweight autoassociative reconstruction for cost-constrained visual anomaly detection","display_name":"Pyramidal inhibitory lightweight autoassociative reconstruction for cost-constrained visual anomaly detection","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225653349","doi":"https://doi.org/10.1007/s44163-026-02671-5"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-026-02671-5","doi":"https://doi.org/10.1007/s44163-026-02671-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-02671-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02671-5.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","oarl"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02671-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059739611","display_name":"Bruno Fernandes","orcid":"https://orcid.org/0000-0002-6001-3925","observed_orcids":["https://orcid.org/0000-0002-6001-3925"]},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR","DE"],"is_corresponding":true,"raw_author_name":"Bruno J. T. Fernandes","raw_affiliation_strings":["Leibniz Universit\u00e4t Hannover, Hannover, Germany","Universidade de Pernambuco, Recife, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-6001-3925","affiliations":[{"raw_affiliation_string":"Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]},{"raw_affiliation_string":"Universidade de Pernambuco, Recife, Brazil","institution_ids":["https://openalex.org/I71437568"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059739611"],"corresponding_institution_ids":["https://openalex.org/I114112103","https://openalex.org/I71437568"],"apc_list":{"value":1590,"currency":"USD","value_usd":1590},"apc_paid":{"value":1590,"currency":"USD","value_usd":1590},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","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":0.9721999764442444,"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":0.9721999764442444,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10036","display_name":"Advanced Neural Network Applications","score":0.004000000189989805,"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/visual-anomaly-detection","display_name":"image anomaly detection","score":0.9929999709129333},{"id":"https://openalex.org/keywords/reconstruction-based-anomaly-detection","display_name":"reconstruction-based anomaly detection","score":0.8199999928474426},{"id":"https://openalex.org/keywords/lateral-inhibition","display_name":"lateral inhibition","score":0.984000027179718},{"id":"https://openalex.org/keywords/lightweight-neural-networks","display_name":"lightweight neural networks","score":0.6980000138282776},{"id":"https://openalex.org/keywords/edge-computing","display_name":"edge computing","score":0.5149999856948853},{"id":"https://openalex.org/keywords/industrial-inspection","display_name":"industrial inspection","score":0.7699999809265137},{"id":"https://openalex.org/keywords/mvtec-ad","display_name":"MVTec AD","score":0.8320000171661377},{"id":"https://openalex.org/keywords/visa","display_name":"Visa","score":0.800000011920929}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7804999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.756600022315979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6442000269889832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5942999720573425},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s44163-026-02671-5","doi":"https://doi.org/10.1007/s44163-026-02671-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-02671-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02671-5.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","oarl"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s44163-026-02671-5","doi":"https://doi.org/10.1007/s44163-026-02671-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-02671-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02671-5.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","oarl"],"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322379","display_name":"Gottfried Wilhelm Leibniz Universit\u00e4t Hannover","ror":"https://ror.org/0304hq317"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225653349.pdf","grobid_xml":"https://content.openalex.org/works/W7225653349.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1970088130","https://openalex.org/W2004209188","https://openalex.org/W2046016430","https://openalex.org/W2100543212","https://openalex.org/W2103646678","https://openalex.org/W2112796928","https://openalex.org/W2132870739","https://openalex.org/W2194775991","https://openalex.org/W2750384547","https://openalex.org/W2948982773","https://openalex.org/W2987228832","https://openalex.org/W3012082538","https://openalex.org/W3034314048","https://openalex.org/W3099658315","https://openalex.org/W3104563483","https://openalex.org/W3109771882","https://openalex.org/W3168175245","https://openalex.org/W3169651898","https://openalex.org/W3183588514","https://openalex.org/W3214308028","https://openalex.org/W4214694907","https://openalex.org/W4225663043","https://openalex.org/W4283331794","https://openalex.org/W4287281153","https://openalex.org/W4297792631","https://openalex.org/W4311313870","https://openalex.org/W4312605624","https://openalex.org/W4313151162","https://openalex.org/W4320024046","https://openalex.org/W4362653662","https://openalex.org/W4385617675","https://openalex.org/W4386065608","https://openalex.org/W4386065890","https://openalex.org/W4387587641","https://openalex.org/W4393153331","https://openalex.org/W4394625793","https://openalex.org/W4400516089","https://openalex.org/W4402978623","https://openalex.org/W4404166214","https://openalex.org/W4404356765","https://openalex.org/W4408579121","https://openalex.org/W4409778244","https://openalex.org/W4410902542","https://openalex.org/W4413592073","https://openalex.org/W7147350932","https://openalex.org/W7154348039","https://openalex.org/W7163061961"],"related_works":["https://openalex.org/W3092704883","https://openalex.org/W4400111402","https://openalex.org/W3044215473","https://openalex.org/W7160177820","https://openalex.org/W7027029673","https://openalex.org/W7221076348","https://openalex.org/W4390872785","https://openalex.org/W7164657117","https://openalex.org/W7220979235","https://openalex.org/W4401243687"],"abstract_inverted_index":{"Abstract":[0],"Visual":[1],"anomaly":[2,31,48,93,130,293],"detection":[3,32,322],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,276,314,329],"industrial":[9,75,235,321],"inspection,":[10],"edge":[11,77],"monitoring":[12],"and":[13,24,67,110,128,166,179,209,223,251,259,298],"visual":[14],"quality":[15],"control,":[16],"particularly":[17],"where":[18],"abnormal":[19],"samples":[20],"are":[21,203,301],"rare,":[22],"heterogeneous,":[23],"often":[25,56],"unavailable":[26],"during":[27,138],"training.":[28],"Recent":[29],"deep":[30],"approaches":[33],"have":[34],"achieved":[35],"high":[36],"classification":[37],"performance":[38],"by":[39],"leveraging":[40],"pretrained":[41],"backbones,":[42],"memory":[43,63,296],"banks,":[44],"nearest-neighbor":[45,152],"search,":[46],"synthetic":[47],"generation,":[49],"or":[50,76,154],"auxiliary":[51],"discriminators.":[52],"However,":[53],"these":[54,201],"methods":[55],"increase":[57],"parameter":[58],"count,":[59],"floating-point":[60],"operations":[61],"(FLOPs),":[62],"usage,":[64],"update":[65],"size,":[66],"energy":[68],"consumption,":[69],"which":[70,328],"complicates":[71],"deployment":[72],"on":[73,160,227,241,269],"cost-constrained":[74],"hardware.":[78],"This":[79],"study":[80],"introduces":[81],"PILAR":[82,95,140,157,189,286],"(Pyramidal":[83],"Inhibitory":[84],"Lightweight":[85],"Autoassociative":[86],"Reconstruction),":[87],"a":[88,97,105,181,291,324],"compact":[89,188],"reconstruction-based":[90],"architecture":[91],"for":[92],"detection.":[94],"employs":[96],"pyramidal":[98],"autoassociative":[99],"encoder-decoder":[100],"with":[101,125,244],"local":[102,115],"receptive":[103],"fields,":[104],"spatial":[106],"bottleneck,":[107],"pure-pyramid":[108],"reconstruction,":[109,172,175,178],"lateral":[111],"inhibition":[112],"to":[113,191,213],"promote":[114],"competition":[116],"within":[117],"feature":[118,195,336],"maps.":[119,196,337],"The":[120,216],"model":[121],"is":[122,132,158,311,332],"trained":[123],"only":[124],"normal":[126],"samples,":[127],"the":[129,198,233,245,270],"score":[131],"obtained":[133,333],"from":[134,205,334],"reconstruction":[135,310],"residuals.":[136],"Thus,":[137],"inference,":[139],"does":[141],"not":[142],"require":[143],"class":[144],"prototypes,":[145],"covariance":[146],"matrices,":[147],"support":[148],"vectors,":[149],"density":[150],"parameters,":[151],"databases,":[153],"discriminator":[155],"states.":[156],"evaluated":[159,199,246],"MNIST,":[161],"Fashion-MNIST,":[162],"CIFAR-10,":[163],"MVTec":[164,228],"AD,":[165],"VisA":[167],"datasets":[168],"using":[169],"direct":[170,308],"image":[171],"whole-image":[173],"RGB":[174,177,309],"patchwise":[176],"Feature-PILAR-FCN,":[180],"fully":[182],"convolutional":[183],"feature-space":[184],"variant":[185],"that":[186,285,307],"uses":[187],"heads":[190],"reconstruct":[192],"selected":[193,315],"frozen":[194,335],"In":[197],"implementation,":[200],"maps":[202],"taken":[204],"ResNet18":[206,247],"layer":[207,210],"2":[208],"3":[211],"prior":[212],"residual":[214],"scoring.":[215],"proposed":[217],"detector":[218,294],"reaches":[219,237],"$$98.86\\pm":[220],"0.04\\%$$":[221],"Image-AP":[222],"$$92.63\\pm":[224],"0.05\\%$$":[225],"AUPRO@30":[226],"AD":[229],"over":[230],"five":[231],"seeds;":[232],"unchanged":[234],"configuration":[236],"$$92.53\\pm":[238],"0.07\\%$$":[239],"Image-AUROC":[240],"VisA.":[242],"Compared":[243],"configurations":[248],"of":[249],"SimpleNet":[250],"GLASS,":[252],"Feature-PILAR-FCN":[253],"retains":[254],"35.6%":[255],"fewer":[256],"inference":[257],"parameters":[258],"achieves":[260],"5.2\u20135.6":[261],"times":[262],"their":[263],"throughput":[264],"at":[265],"batch":[266],"size":[267],"16":[268],"same":[271],"Apple":[272],"M4":[273],"Max":[274],"GPU":[275],"FP32,":[277],"despite":[278],"higher":[279],"single-image":[280],"latency.":[281],"These":[282],"results":[283],"indicate":[284],"can":[287],"be":[288],"used":[289],"as":[290],"low-state":[292],"when":[295],"footprint":[297],"computational":[299],"cost":[300],"relevant":[302],"constraints.":[303],"They":[304],"also":[305],"show":[306],"useful":[312],"mainly":[313],"low-cost":[316],"screening":[317],"cases,":[318],"while":[319],"broader":[320],"requires":[323],"more":[325],"informative":[326],"representation,":[327],"this":[330],"work":[331]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}