{"id":"https://openalex.org/W4417073174","doi":"https://doi.org/10.1145/3743093.3770997","title":"CARD: Control-Driven Autoregressive Reconstruction with Decoupled Learning for Multi-Class Anomaly Detection","display_name":"CARD: Control-Driven Autoregressive Reconstruction with Decoupled Learning for Multi-Class Anomaly Detection","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073174","doi":"https://doi.org/10.1145/3743093.3770997"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770997","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770997","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770997","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770997","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038457959","display_name":"Yifan Wang","orcid":"https://orcid.org/0009-0008-4455-8264"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["Institution of Automation, Chinese Academy of Science, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institution of Automation, Chinese Academy of Science, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035826085","display_name":"Mingqing Wang","orcid":"https://orcid.org/0009-0008-2517-0731"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqing Wang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113330446","display_name":"Boyi Sun","orcid":"https://orcid.org/0009-0005-6780-7495"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyi Sun","raw_affiliation_strings":["Institution of Automation, Chinese Academy of Science, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institution of Automation, Chinese Academy of Science, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303961","display_name":"Qianfan Zhao","orcid":"https://orcid.org/0000-0003-2521-7006"},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianfan Zhao","raw_affiliation_strings":["Research and Development, Hangzhou Xingwuzhong Robot Co., Ltd, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Research and Development, Hangzhou Xingwuzhong Robot Co., Ltd, Hangzhou, China","institution_ids":["https://openalex.org/I4210144102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101959190","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0001-6240-5300"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Institution of Automation, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institution of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434504","display_name":"Zhiyong Liu","orcid":"https://orcid.org/0000-0003-2148-1846"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Liu","raw_affiliation_strings":["Institution of Automation, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institution of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007963696","display_name":"Xu Yang","orcid":"https://orcid.org/0000-0003-0553-4581"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["Institution of Automation, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institution of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031113517","display_name":"Suiwu Zheng","orcid":"https://orcid.org/0000-0001-8068-0883"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suiwu Zheng","raw_affiliation_strings":["Institution of Automation, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institution of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5038457959"],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21525351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9513999819755554,"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":0.9513999819755554,"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":0.007699999958276749,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/autoregressive-model","display_name":"Autoregressive model","score":0.7272999882698059},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5863000154495239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.492900013923645},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.491100013256073},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4027999937534332},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3790999948978424},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.32089999318122864}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7272999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5993000268936157},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5823000073432922},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.491100013256073},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2671000063419342},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770997","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770997","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770997","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3770997","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770997","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770997","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073174.pdf","grobid_xml":"https://content.openalex.org/works/W4417073174.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1966832848","https://openalex.org/W2194775991","https://openalex.org/W2962785568","https://openalex.org/W2964137095","https://openalex.org/W3165699580","https://openalex.org/W3169651898","https://openalex.org/W3180355996","https://openalex.org/W3209793239","https://openalex.org/W4214694907","https://openalex.org/W4312605624","https://openalex.org/W4312772600","https://openalex.org/W4320476215","https://openalex.org/W4386065385","https://openalex.org/W4386065608","https://openalex.org/W4386065890","https://openalex.org/W4390872231","https://openalex.org/W4390872580","https://openalex.org/W4392903760","https://openalex.org/W4393147759"],"related_works":[],"abstract_inverted_index":{"Multi-class":[0],"unsupervised":[1],"anomaly":[2,34,148],"detection":[3],"(UAD)":[4],"is":[5],"challenging":[6],"due":[7],"to":[8,45,89,120,134,138,145],"the":[9,36,52,116,122,135,143,171,182,188,198,204],"difficulty":[10],"of":[11,38,54,184,195],"harmonizing":[12],"distributional":[13],"differences":[14],"across":[15],"categories":[16],"within":[17,93],"a":[18,64,85,103,126],"unified":[19],"framework.":[20],"While":[21],"recent":[22],"diffusion-based":[23],"methods":[24],"have":[25],"demonstrated":[26],"promising":[27],"performance":[28],"by":[29,51,166],"leveraging":[30],"denoising":[31],"processes":[32],"for":[33,73],"reconstruction,":[35,160],"lack":[37],"explicit":[39,97],"causal":[40,91],"constraints":[41],"limits":[42],"their":[43],"ability":[44],"handle":[46],"complex":[47],"logical":[48,60],"inconsistencies.":[49],"Inspired":[50],"success":[53],"autoregressive":[55,87,118],"models":[56],"in":[57,170],"enforcing":[58],"local-to-global":[59],"consistency,":[61],"we":[62,101,131],"propose":[63],"Control-driven":[65],"Autoregressive":[66],"Reconstruction":[67,105],"with":[68],"Decoupled":[69],"learning":[70,158],"(CARD)":[71],"framework":[72],"multi-class":[74],"UAD.":[75],"It":[76],"first":[77],"tokenizes":[78],"images":[79],"using":[80],"vector":[81],"quantization":[82],"and":[83,201],"employs":[84],"vision":[86],"model":[88,119,144],"capture":[90],"dependencies":[92],"normal":[94,156],"patterns":[95],"as":[96,112],"prior":[98,151],"knowledge.":[99],"Then,":[100],"introduce":[102],"Control-Driven":[104],"(CDR)":[106],"network,":[107],"which":[108],"aligns":[109],"input":[110,137],"features":[111,149],"control":[113],"signals":[114],"into":[115],"frozen":[117],"adjust":[121],"predicted":[123],"distribution,":[124],"enabling":[125],"generative":[127],"reconstruction":[128],"process.":[129],"Additionally,":[130],"apply":[132],"perturbations":[133],"CDR":[136],"simulate":[139],"anomalous":[140],"conditions,":[141],"facilitating":[142],"correct":[146],"out-of-distribution":[147],"under":[150],"knowledge":[152],"constraints.":[153],"By":[154],"decoupling":[155],"pattern":[157],"from":[159],"CARD":[161,191],"prevents":[162],"identity":[163],"mapping":[164],"caused":[165],"forgetting":[167],"implicit":[168],"priors":[169],"conventional":[172],"reconstruction-based":[173],"method.":[174],"Comprehensive":[175],"experiments":[176],"on":[177],"several":[178],"benchmark":[179],"datasets":[180],"validate":[181],"effectiveness":[183],"our":[185],"approach.":[186],"On":[187],"MVTecAD":[189],"dataset,":[190],"achieved":[192],"AUROC":[193],"scores":[194],"98.7%":[196],"at":[197,203],"image":[199],"level":[200],"98.5%":[202],"pixel":[205],"level.":[206]},"counts_by_year":[],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-12-06T00:00:00"}