{"id":"https://openalex.org/W7162537489","doi":"https://doi.org/10.48550/arxiv.2605.26676","title":"Memory-Distilled Selection for Noise-Robust Anomaly Detection","display_name":"Memory-Distilled Selection for Noise-Robust Anomaly Detection","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162537489","doi":"https://doi.org/10.48550/arxiv.2605.26676"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26676","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26676","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26676","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033470550","display_name":"Sirojbek Safarov","orcid":"https://orcid.org/0000-0001-5724-3271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Safarov, Sirojbek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137162635","display_name":"Jaewoo Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Jaewoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103119385","display_name":"Yoon Gyo Jung","orcid":"https://orcid.org/0000-0002-0945-4311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Yoon Gyo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063443405","display_name":"Kuan\u2013Chuan Peng","orcid":"https://orcid.org/0000-0002-2682-9912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Kuan-Chuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137173548","display_name":"Wonchul Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Wonchul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110555346","display_name":"Seongdeok Bang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bang, Seongdeok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061661661","display_name":"OCTAVIA CAMPS","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Camps, Octavia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.964900016784668,"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":0.964900016784668,"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":0.004999999888241291,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0044999998062849045,"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/noise","display_name":"Noise (video)","score":0.7386000156402588},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.649399995803833},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6331999897956848},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5368000268936157},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5300999879837036},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.508400022983551},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.49149999022483826}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7386000156402588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542999744415283},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.649399995803833},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.49149999022483826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48969998955726624},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4471000134944916},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C55352655","wikidata":"https://www.wikidata.org/wiki/Q304247","display_name":"Median filter","level":4,"score":0.30239999294281006},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C50151734","wikidata":"https://www.wikidata.org/wiki/Q1759577","display_name":"Matched filter","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26676","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26676","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26676","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26676","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.612576425075531}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Anomaly":[0],"detection":[1,12],"(AD)":[2],"under":[3,160,174],"data":[4,53,112,176],"contamination":[5],"is":[6,22,107,126],"critical":[7],"for":[8],"deploying":[9],"unsupervised":[10],"defect":[11],"in":[13],"industrial":[14,171],"environments,":[15],"where":[16,65],"curating":[17],"perfectly":[18],"clean":[19,111],"training":[20,49],"sets":[21],"impractical.":[23],"However,":[24],"existing":[25],"methods":[26],"are":[27,98],"sensitive":[28],"to":[29,94],"contamination,":[30],"suffering":[31],"significant":[32],"performance":[33,154],"degradation":[34],"as":[35,70],"the":[36,66,95,117,166],"noise":[37,83,133,149],"ratio":[38],"increases.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"propose":[44],"Memory-Distilled":[45],"Selection":[46],"(MeDS),":[47],"a":[48,71,79,102,129,147],"algorithm":[50],"based":[51],"on":[52,110,144,155,170],"selection.":[54],"MeDS":[55,125,169],"constructs":[56],"an":[57],"ensemble":[58],"of":[59,82,88,123,132,168],"partial":[60],"memories":[61,97],"via":[62],"random":[63],"subsampling,":[64],"resulting":[67],"sparsity":[68],"acts":[69],"low-pass":[72],"filter":[73],"that":[74],"captures":[75],"nominal":[76],"patterns":[77],"across":[78,128],"wide":[80,130],"range":[81,131],"ratios,":[84],"enabling":[85,120],"coarse-level":[86],"identification":[87],"contaminated":[89],"samples.":[90],"The":[91],"aggregated":[92],"distances":[93],"bootstrapped":[96],"then":[99],"distilled":[100,118],"into":[101],"reconstruction":[103],"score":[104],"network,":[105],"which":[106],"subsequently":[108],"fine-tuned":[109],"filtered":[113],"using":[114],"scores":[115],"from":[116],"model,":[119],"fine-grained":[121],"localization":[122],"anomalies.":[124],"robust":[127],"ratios":[134],"without":[135],"requiring":[136],"noise-ratio-specific":[137],"hyperparameter":[138],"tuning,":[139],"achieving":[140],"99.16\\%":[141],"image-level":[142],"AUROC":[143],"MVTecAD":[145],"at":[146],"40\\%":[148],"ratio,":[150],"and":[151,158],"attaining":[152],"state-of-the-art":[153],"both":[156],"VisA":[157],"Real-IAD":[159],"noisy":[161,175],"settings.":[162],"We":[163],"thoroughly":[164],"verify":[165],"efficacy":[167],"AD":[172],"benchmarks":[173],"scenarios,":[177],"accompanied":[178],"by":[179],"in-depth":[180],"empirical":[181],"analyses.":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}