{"id":"https://openalex.org/W7159774770","doi":"https://doi.org/10.1109/tip.2026.3687095","title":"Dual-Masked and Discriminative Reconstruction for Unified Vision Anomaly Detection","display_name":"Dual-Masked and Discriminative Reconstruction for Unified Vision Anomaly Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7159774770","doi":"https://doi.org/10.1109/tip.2026.3687095","pmid":"https://pubmed.ncbi.nlm.nih.gov/42065980"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3687095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3687095","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135001969","display_name":"Bin-Bin Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin-Bin Gao","raw_affiliation_strings":["Tencent YouTu Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2572-8156","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5135001969"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50740214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4701","last_page":"4712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9818000197410583,"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":0.9818000197410583,"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":0.0024999999441206455,"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":0.002300000051036477,"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":0.8271999955177307},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.7426999807357788},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7127000093460083},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6973999738693237},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6287999749183655},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6262999773025513}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.8271999955177307},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.7426999807357788},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7127000093460083},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6973999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6952999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517000198364258},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6262999773025513},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3687095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3687095","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42065980","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42065980","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.741226077079773}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"reconstruction":[1,58,207,225],"networks":[2,59],"have":[3,86],"shown":[4],"promise":[5],"for":[6,44,92,165,272],"unified":[7,166],"vision":[8,167],"anomaly":[9,13,17,72,127,136,145,168,211,238],"detection,":[10],"i.e.,":[11,41,177],"image-level":[12],"classification":[14],"and":[15,71,78,98,108,118,144,161,220,226,257,259,267],"pixel-level":[16],"segmentation,":[18],"where":[19,68,142],"a":[20,51,116,156,173,179,202],"single":[21],"model":[22,43],"trained":[23],"on":[24,88,251],"multi-class":[25],"normal":[26,70,143,219],"images":[27,73,212],"can":[28,229],"detect":[29],"various":[30],"anomalies.":[31,83],"This":[32],"is":[33,102,274],"more":[34,52,119],"challenging":[35],"than":[36],"most":[37,123],"existing":[38,124],"separate":[39],"methods,":[40],"one":[42,45],"class,":[46],"as":[47,130,231],"it":[48,101],"requires":[49],"handling":[50],"complex":[53],"data":[54],"distribution.":[55],"Notably,":[56],"pure":[57],"often":[60],"suffer":[61],"from":[62,112],"overfitting":[63],"due":[64,138],"to":[65,106,139,213],"\"identity":[66,186],"shortcut\",":[67],"both":[69],"may":[74,147],"be":[75,148],"well":[76],"recovered":[77],"thus":[79],"fail":[80],"in":[81,115,134],"detecting":[82],"Recent":[84],"efforts":[85],"focused":[87],"developing":[89],"specific":[90],"modules":[91],"different":[93],"network":[94],"architectures,":[95],"e.g.,":[96],"Convolutions":[97],"Transformers.":[99],"However,":[100],"still":[103],"unclear":[104],"how":[105],"essentially":[107],"effectively":[109],"prevent":[110],"learning":[111],"this":[113],"shortcut":[114],"simpler":[117],"general":[120,159,174],"manner.":[121],"Furthermore,":[122],"methods":[125,240,250],"consider":[126],"detection":[128,239],"solely":[129],"unsupervised":[131],"classification,":[132],"resulting":[133],"inaccurate":[135],"segmentation":[137],"\"weak":[140],"discrimination\",":[141],"features":[146],"entangled.":[149],"To":[150],"address":[151],"these":[152],"challenges,":[153],"we":[154,171,200],"propose":[155,172,201],"simple":[157],"yet":[158],"Dual-masked":[160],"Discriminative":[162],"Reconstruction":[163],"(D2Rec)":[164],"detection.":[169],"First,":[170],"dual-masked":[175,224],"reconstruction,":[176],"using":[178],"pair":[180],"of":[181,241],"complementary":[182],"masks,":[183],"resolving":[184],"the":[185,215],"shortcut\"":[187],"so":[188],"that":[189],"all":[190],"masked":[191],"positions":[192],"are":[193],"reconstructed":[194],"by":[195],"unmasked":[196],"original":[197],"features.":[198,222],"Second,":[199],"self-supervised":[203,227],"discriminator,":[204],"which":[205],"refines":[206],"errors":[208],"with":[209],"synthesized":[210],"enhance":[214],"discrimination":[216],"ability":[217],"between":[218],"abnormal":[221],"The":[223,270],"discriminator":[228],"serve":[230],"universal":[232],"plugins,":[233],"easily":[234],"integrated":[235],"into":[236],"reconstruction-based":[237],"any":[242],"architecture.":[243],"Despite":[244],"its":[245],"simplicity,":[246],"D2Rec":[247,273],"outperforms":[248],"previous":[249],"three":[252,260],"industrial":[253],"benchmarks":[254],"(MVTec,":[255],"BTAD,":[256],"VisA),":[258],"medical":[261],"datasets":[262],"(Brain":[263],"MRI,":[264],"Liver":[265],"CT":[266],"Retinal":[268],"OCT).":[269],"code":[271],"available":[275],"at":[276],"https://github.com/gaobb/D2Rec.":[277]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2026-05-03T00:00:00"}