{"id":"https://openalex.org/W7164857753","doi":"https://doi.org/10.1145/3805622.3810738","title":"SAND: Semantic-Aware Anomaly Detection with Region-Consistent Memory for Noisy Training","display_name":"SAND: Semantic-Aware Anomaly Detection with Region-Consistent Memory for Noisy Training","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164857753","doi":"https://doi.org/10.1145/3805622.3810738"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810738","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810738","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100665809","display_name":"Ke Xu","orcid":"https://orcid.org/0000-0001-8669-3909"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixi Xu","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-2210-0653","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006557503","display_name":"Y Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyang Zhang","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8067-8414","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644814","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0002-8951-2648"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilong Liu","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-6927-8134","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138639564","display_name":"Zirui Luo","orcid":"https://orcid.org/0009-0005-0539-1180"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zirui Luo","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-0539-1180","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138649412","display_name":"Yutong He","orcid":"https://orcid.org/0009-0006-3264-809X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong He","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-3264-809X","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100704268","display_name":"Li Yao","orcid":"https://orcid.org/0000-0003-2930-8407"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yao","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2930-8407","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"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":"2228","last_page":"2236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.90420001745224,"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":0.90420001745224,"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":0.02160000056028366,"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":0.012500000186264515,"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":0.738099992275238},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5306000113487244},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5187000036239624},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4650999903678894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4505999982357025},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4156999886035919},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40639999508857727}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.738099992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113000154495239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849000215530396},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5187000036239624},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4650999903678894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4156999886035919},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810738","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810738","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6676151156425476,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W3034552520","https://openalex.org/W3147184966","https://openalex.org/W3166166117","https://openalex.org/W3169651898","https://openalex.org/W3183588514","https://openalex.org/W3200904534","https://openalex.org/W4214694907","https://openalex.org/W4292851291","https://openalex.org/W4312570668","https://openalex.org/W4312605624","https://openalex.org/W4386065385","https://openalex.org/W4386065608","https://openalex.org/W4386065890","https://openalex.org/W4386075649","https://openalex.org/W4390874443","https://openalex.org/W4391992447","https://openalex.org/W4393158476","https://openalex.org/W4394625793","https://openalex.org/W4402716302","https://openalex.org/W4402915908","https://openalex.org/W4405622487","https://openalex.org/W4409262527","https://openalex.org/W4409364302","https://openalex.org/W4413144853","https://openalex.org/W4413145755","https://openalex.org/W4413146114","https://openalex.org/W4413157177","https://openalex.org/W7133213090","https://openalex.org/W7133227337","https://openalex.org/W7135018735","https://openalex.org/W7138126727","https://openalex.org/W7160018799"],"related_works":[],"abstract_inverted_index":{"Industrial":[0],"anomaly":[1,59,135,195],"detection":[2,60,160,196],"is":[3,97],"typically":[4],"trained":[5],"under":[6,61,146],"the":[7,86,188],"assumption":[8],"of":[9,137,190],"clean":[10],"normal":[11],"data,":[12],"yet":[13],"real-world":[14],"manufacturing":[15],"datasets":[16],"are":[17,29],"often":[18],"contaminated":[19],"by":[20],"unlabeled":[21],"defects":[22],"and":[23,130,144,161,197],"background":[24,152],"outliers.":[25],"Global":[26],"memory-based":[27],"detectors":[28],"especially":[30],"fragile":[31],"in":[32,157,165,193],"such":[33],"noisy":[34,62,194],"regimes:":[35],"semantic":[36,68,73,88,174,191],"mismatch":[37],"across":[38],"regions":[39],"can":[40],"induce":[41],"erroneous":[42],"retrieval,":[43,178],"while":[44],"boundary-crossing":[45],"patches":[46],"yield":[47],"ambiguous":[48],"pseudo":[49,117],"supervision.":[50],"We":[51,119],"propose":[52,121],"SAND,":[53],"a":[54,78,91,122,199],"semantic-aware":[55],"framework":[56],"for":[57,182],"unsupervised":[58],"training":[63],"data":[64],"that":[65,82,126],"leverages":[66],"training-only":[67],"priors":[69,175],"derived":[70],"from":[71],"pre-computed":[72],"region":[74,95],"partitions.":[75],"SAND":[76,169],"introduces":[77],"region-consistent":[79],"memory":[80],"design":[81],"constrains":[83],"retrieval":[84],"to":[85,114],"same":[87],"region,":[89],"with":[90,111],"global":[92],"fallback":[93],"when":[94],"assignment":[96],"uncertain,":[98],"reducing":[99],"cross-region":[100],"aliasing.":[101],"To":[102],"further":[103],"stabilize":[104],"learning,":[105],"we":[106],"develop":[107],"purity-aware":[108],"soft":[109],"weighting":[110],"adaptive":[112],"thresholds":[113],"downweight":[115],"boundary-ambiguous":[116],"labels.":[118],"additionally":[120],"region-wise":[123],"representation":[124],"regularizer":[125],"enforces":[127],"intra-region":[128],"compactness":[129],"inter-region":[131],"separation,":[132],"thereby":[133],"mitigating":[134],"contamination":[136],"prototypes.":[138],"Extensive":[139],"experiments":[140],"on":[141],"MVTec":[142],"AD":[143],"VisA":[145],"multiple":[147],"noise":[148],"protocols,":[149],"including":[150],"realistic":[151],"perturbations,":[153],"demonstrate":[154],"consistent":[155],"improvements":[156],"both":[158],"image-level":[159],"pixel-level":[162],"localization,":[163],"particularly":[164],"multi-object":[166],"scenarios.":[167],"Notably,":[168],"achieves":[170],"these":[171],"gains":[172],"without":[173],"or":[176],"test-time":[177],"supporting":[179],"efficient":[180],"inference":[181],"practical":[183,200],"deployment.":[184,205],"Our":[185],"results":[186],"highlight":[187],"importance":[189],"provenance":[192],"suggest":[198],"pathway":[201],"toward":[202],"robust":[203],"industrial":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-16T00:00:00"}