{"id":"https://openalex.org/W4416454351","doi":"https://doi.org/10.48550/arxiv.2511.11934","title":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","display_name":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416454351","doi":"https://doi.org/10.48550/arxiv.2511.11934"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.11934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.11934","pdf_url":"https://arxiv.org/pdf/2511.11934","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.11934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090790158","display_name":"Cecilia Olivares","orcid":"https://orcid.org/0000-0003-0149-1270"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Olivares, Claudio C\u00e9sar Claros","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103119412","display_name":"Austin J. Brockmeier","orcid":"https://orcid.org/0000-0002-7293-8140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brockmeier, Austin J.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090790158"],"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5023999810218811,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5023999810218811,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.07129999995231628,"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":0.04989999905228615,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5878000259399414},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5713000297546387},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5327000021934509},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4187000095844269},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3718999922275543},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3686999976634979},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.3544999957084656},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.35249999165534973}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7473000288009644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029999852180481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5713000297546387},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5327000021934509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26840001344680786},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2511.11934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.11934","pdf_url":"https://arxiv.org/pdf/2511.11934","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2511.11934","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2511.11934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.11934","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.11934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.11934","pdf_url":"https://arxiv.org/pdf/2511.11934","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"We":[0,159],"present":[1],"the":[2,33,58,114],"largest":[3],"systematic":[4],"comparison":[5,21],"to":[6],"date":[7],"of":[8,25,32,40,47],"out-of-distribution":[9,34],"(OOD)":[10],"detection":[11],"methods":[12],"using":[13],"AURC":[14],"and":[15,42,61,67,86,96,108,125,152,169,185],"AUGRC":[16],"as":[17],"primary":[18],"metrics.":[19],"Our":[20],"explores":[22],"different":[23],"regimes":[24],"distribution":[26,75],"shift":[27],"(stratified":[28],"by":[29],"CLIP":[30],"embeddings":[31],"image":[35],"datasets)":[36],"with":[37,105],"varying":[38],"numbers":[39],"classes":[41],"uses":[43],"a":[44,87,99,162,171],"representation-centric":[45],"view":[46],"OOD":[48,120],"detection,":[49],"including":[50],"neural":[51],"collapse":[52],"metrics,":[53],"for":[54,71,165],"subsequent":[55],"analysis.":[56],"Together":[57],"empirical":[59],"results":[60],"representation":[62,80],"analysis":[63,181],"provides":[64],"novel":[65],"insights":[66],"statistically":[68],"grounded":[69],"guidance":[70],"method":[72],"selection":[73],"under":[74,190],"shift.":[76],"Experiments":[77],"cover":[78],"two":[79],"paradigms:":[81],"CNNs":[82,124],"trained":[83],"from":[84],"scratch":[85],"fine-tuned":[88],"Vision":[89],"Transformer":[90],"(ViT),":[91],"evaluated":[92],"on":[93,146,149],"CIFAR-10/100,":[94],"SuperCIFAR-100,":[95],"TinyImageNet.":[97],"Using":[98],"multiple-comparison-controlled,":[100],"rank-based":[101],"pipeline":[102],"(Friedman":[103],"test":[104],"Conover-Holm":[106],"post-hoc)":[107],"Bron-Kerbosch":[109],"cliques,":[110],"we":[111],"find":[112],"that":[113,170],"learned":[115],"feature":[116],"space":[117],"largely":[118],"determines":[119],"efficacy.":[121],"For":[122],"both":[123],"ViTs,":[126],"probabilistic":[127],"scores":[128,140,187],"(e.g.,":[129,141],"MSR,":[130],"GEN)":[131],"dominate":[132],"misclassification":[133],"(ID)":[134],"detection.":[135],"Under":[136],"stronger":[137],"shifts,":[138],"geometry-aware":[139],"NNGuide,":[142],"fDBD,":[143],"CTM)":[144],"prevail":[145],"CNNs,":[147],"whereas":[148],"ViTs":[150],"GradNorm":[151],"KPCA":[153],"Reconstruction":[154],"Error":[155],"remain":[156],"consistently":[157],"competitive.":[158],"further":[160],"show":[161],"class-count-dependent":[163],"trade-off":[164],"Monte-Carlo":[166],"Dropout":[167],"(MCD)":[168],"simple":[172],"PCA":[173],"projection":[174],"improves":[175],"several":[176],"detectors.":[177],"The":[178],"neural-collapse-based":[179],"geometric":[180],"explains":[182],"when":[183],"prototype":[184],"boundary-based":[186],"become":[188],"optimal":[189],"strong":[191],"shifts.":[192]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-11-19T00:00:00"}