{"id":"https://openalex.org/W7151521898","doi":"https://doi.org/10.48550/arxiv.2604.04632","title":"InCTRLv2: Generalist Residual Models for Few-Shot Anomaly Detection and Segmentation","display_name":"InCTRLv2: Generalist Residual Models for Few-Shot Anomaly Detection and Segmentation","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7151521898","doi":"https://doi.org/10.48550/arxiv.2604.04632"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.04632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04632","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.04632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038211659","display_name":"Jiawen Zhu","orcid":"https://orcid.org/0000-0002-9260-6151"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jiawen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051914600","display_name":"Mengjia Niu","orcid":"https://orcid.org/0009-0002-5442-3730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Mengjia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039104219","display_name":"Guansong Pang","orcid":"https://orcid.org/0000-0002-9877-2716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Guansong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.9883000254631042,"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":0.9883000254631042,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.0013000000035390258,"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":0.7937999963760376},{"id":"https://openalex.org/keywords/abnormality","display_name":"Abnormality","score":0.6190000176429749},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5996000170707703},{"id":"https://openalex.org/keywords/normality","display_name":"Normality","score":0.579800009727478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5584999918937683},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5436999797821045},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5141000151634216},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.42489999532699585}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7937999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6700000166893005},{"id":"https://openalex.org/C50965678","wikidata":"https://www.wikidata.org/wiki/Q2724302","display_name":"Abnormality","level":2,"score":0.6190000176429749},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.531000018119812},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4172999858856201},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3050999939441681},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.04632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04632","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.04632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04632","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7436202764511108,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"recent":[1,55],"anomaly":[2,123,258],"detection":[3,259],"(AD)":[4],"methods":[5],"have":[6],"made":[7],"substantial":[8],"progress":[9],"in":[10,54,114,150,193,256],"recognizing":[11],"abnormal":[12,148],"patterns":[13,192],"within":[14],"specific":[15,32],"domains,":[16],"most":[17],"of":[18,47,102,122,166,208],"them":[19],"are":[20,24,213],"specialist":[21],"models":[22],"that":[23,89,162,251],"trained":[25],"on":[26,99,202,246],"large":[27],"training":[28],"samples":[29,168],"from":[30,169],"a":[31,60,79,126,156,194,228],"target":[33],"dataset,":[34],"struggling":[35],"to":[36,38,58,64,110],"generalize":[37],"unseen":[39],"datasets.":[40],"To":[41,72],"address":[42],"this":[43,73,75],"limitation,":[44],"the":[45,100,151,164,171,185,206,239],"paradigm":[46],"Generalist":[48,82],"Anomaly":[49,83,140,179],"Detection":[50,84],"(GAD)":[51],"has":[52],"emerged":[53],"years,":[56],"aiming":[57],"learn":[59],"single":[61],"generalist":[62],"model":[63],"detect":[65,111],"anomalies":[66,112,204],"across":[67,263],"diverse":[68],"domains":[69],"without":[70],"retraining.":[71],"end,":[74],"work":[76],"introduces":[77,117],"InCTRLv2,":[78],"novel":[80,134],"few-shot":[81,107],"and":[85,147,159,173,176,260],"Segmentation":[86],"(GADS)":[87],"framework":[88],"significantly":[90],"extends":[91],"our":[92],"previously":[93],"proposed":[94],"GAD":[95],"model,":[96],"InCTRL.":[97],"Building":[98],"idea":[101],"learning":[103],"in-context":[104],"residuals":[105],"with":[106,144],"normal":[108,146,186],"examples":[109],"as":[113],"InCTRL,":[115],"InCTRLv2":[116,252],"two":[118,133],"new,":[119],"complementary":[120],"perspectives":[121],"perception":[124],"under":[125],"dual-branch":[127],"framework.":[128],"This":[129],"is":[130],"accomplished":[131],"by":[132,215,221],"modules":[135],"upon":[136],"InCTRL:":[137],"i)":[138],"Discriminative":[139],"Score":[141,180],"Learning":[142,181],"(DASL)":[143],"both":[145,170,257],"data":[149],"main":[152],"branch,":[153,200],"which":[154,188],"learns":[155,189],"semantic-guided":[157],"abnormality":[158,172],"normality":[160,174,191,209],"space":[161,196],"supports":[163],"classification":[165],"query":[167],"perspectives;":[175],"ii)":[177],"One-class":[178],"(OASL)":[182],"using":[183],"only":[184],"data,":[187],"generalized":[190],"semantic":[195,218,230],"via":[197],"an":[198],"auxiliary":[199],"focusing":[201],"detecting":[203],"through":[205],"lens":[207],"solely.":[210],"Both":[211],"branches":[212],"guided":[214],"rich":[216],"visual-text":[217],"priors":[219],"encoded":[220],"large-scale":[222],"vision-language":[223],"models.":[224],"Together,":[225],"they":[226],"offer":[227],"dual":[229],"perspective":[231],"for":[232],"AD:":[233],"one":[234],"emphasizes":[235,241],"normal-abnormal":[236],"discriminations,":[237],"while":[238],"other":[240],"normality-deviated":[242],"semantics.":[243],"Extensive":[244],"experiments":[245],"ten":[247],"AD":[248],"datasets":[249],"demonstrate":[250],"achieves":[253],"SotA":[254],"performance":[255],"segmentation":[261],"tasks":[262],"various":[264],"settings.":[265]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}