{"id":"https://openalex.org/W7162653596","doi":"https://doi.org/10.48550/arxiv.2605.28021","title":"AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels","display_name":"AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162653596","doi":"https://doi.org/10.48550/arxiv.2605.28021"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28021","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28021","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.28021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114236921","display_name":"Fengqiang Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Fengqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064050872","display_name":"Qing-Yuan Jiang","orcid":"https://orcid.org/0000-0002-9214-7960"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Qing-Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137250654","display_name":"Yang Yang","orcid":"https://orcid.org/0009-0008-3080-9288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yang","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":0.42640000581741333,"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":0.42640000581741333,"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":0.40310001373291016,"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":0.03799999877810478,"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/outlier","display_name":"Outlier","score":0.7910000085830688},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.734000027179718},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.64410001039505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4377000033855438},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4120999872684479},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4059999883174896},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.37630000710487366}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7910000085830688},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.734000027179718},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.64410001039505},{"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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479000210762024},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2574999928474426},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28021","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28021","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.28021","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28021","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Out-of-distribution":[0],"(OOD)":[1],"detection":[2,44,125],"is":[3],"essential":[4],"for":[5,160],"deploying":[6],"machine":[7],"learning":[8],"models":[9],"in":[10],"open-world":[11],"and":[12,24,59,97,194,212],"safety-critical":[13],"scenarios,":[14],"where":[15,163],"test":[16],"inputs":[17],"may":[18],"deviate":[19],"from":[20,156],"the":[21,54,75,92,101,164,168,188,199,214,223],"training":[22,51],"distribution":[23,170],"overconfident":[25,209],"predictions":[26,159,211],"on":[27],"unknown":[28],"samples":[29,79,96,180,193],"can":[30,120],"lead":[31],"to":[32,52,73,105,146,202],"unreliable":[33],"decisions.":[34],"Outlier":[35],"Exposure":[36],"(OE)":[37],"has":[38],"emerged":[39],"as":[40],"a":[41,106,137,204],"promising":[42],"OOD":[43,60,78,95,124,161,179,192,210],"paradigm":[45],"by":[46,69,128],"introducing":[47],"auxiliary":[48],"outliers":[49],"during":[50],"enlarge":[53,66],"margin":[55,68,108],"between":[56,94,191],"in-distribution":[57],"(ID)":[58],"samples.":[61],"Existing":[62],"OE-based":[63],"methods":[64],"typically":[65],"this":[67,129],"employing":[70],"uniform":[71,88],"labels":[72,89],"maximize":[74],"entropy":[76],"of":[77,225],"over":[80],"ID":[81,98,195],"categories.":[82],"However,":[83],"we":[84,131],"theoretically":[85],"show":[86],"that":[87,115,142],"inevitably":[90],"disregard":[91],"relations":[93,119],"categories,":[99],"termed":[100],"over-softening":[102],"effect,":[103],"leading":[104],"suboptimal":[107],"bound.":[109],"Our":[110],"theoretical":[111],"analysis":[112],"further":[113],"reveals":[114],"explicitly":[116],"exploiting":[117],"such":[118],"instead":[121],"yield":[122],"improved":[123],"performance.":[126],"Motivated":[127],"insight,":[130],"propose":[132],"\\underline{A}daptive":[133],"Confidence":[134],"\\underline{OE}":[135],"(AOE),":[136],"simple":[138],"yet":[139],"effective":[140],"method":[141],"leverages":[143],"temperature":[144,166],"scaling":[145],"recalibrate":[147],"outlier":[148],"labels.":[149],"Specifically,":[150],"AOE":[151,186],"generates":[152],"adaptive":[153,183],"soft":[154,184],"targets":[155,201],"temperature-scaled":[157],"model":[158],"samples,":[162],"learnable":[165],"smooths":[167],"prediction":[169],"without":[171],"fully":[172],"erasing":[173],"class-wise":[174],"relational":[175],"information.":[176],"By":[177],"supervising":[178],"with":[181],"these":[182],"targets,":[185],"preserves":[187],"semantic":[189],"proximity":[190],"categories":[196],"while":[197],"encouraging":[198],"softened":[200],"approach":[203],"high-entropy":[205],"distribution,":[206],"thereby":[207],"suppressing":[208],"enlarging":[213],"separation":[215],"margin.":[216],"Extensive":[217],"experiments":[218],"across":[219],"diverse":[220],"benchmarks":[221],"demonstrate":[222],"effectiveness":[224],"AOE.":[226]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}