{"id":"https://openalex.org/W4407567451","doi":"https://doi.org/10.1007/s10994-024-06693-x","title":"Re-assessing accuracy degradation: a framework for understanding DNN behavior on similar-but-non-identical test datasets","display_name":"Re-assessing accuracy degradation: a framework for understanding DNN behavior on similar-but-non-identical test datasets","publication_year":2025,"publication_date":"2025-02-14","ids":{"openalex":"https://openalex.org/W4407567451","doi":"https://doi.org/10.1007/s10994-024-06693-x"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-024-06693-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06693-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06693-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06693-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068577161","display_name":"Esla Timothy Anzaku","orcid":"https://orcid.org/0009-0005-7723-159X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210132857","display_name":"Ghent University Global Campus","ror":"https://ror.org/041bygf77","country_code":"KR","type":"education","lineage":["https://openalex.org/I32597200","https://openalex.org/I4210132857"]}],"countries":["BE","KR"],"is_corresponding":true,"raw_author_name":"Esla Timothy Anzaku","raw_affiliation_strings":["Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Munhwa-ro 119-5, Incheon, 21985, South Korea","Department of Electronics and Information Systems, Ghent University, Technologiepark-Zwijnaarde 126, 9052, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Munhwa-ro 119-5, Incheon, 21985, South Korea","institution_ids":["https://openalex.org/I4210132857"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Technologiepark-Zwijnaarde 126, 9052, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101892837","display_name":"Haohan Wang","orcid":"https://orcid.org/0000-0002-1826-4069"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haohan Wang","raw_affiliation_strings":["School of Information Sciences, University of Illionois Urbana-Champaign, 501 E. Daniel St. MC-493, Champaign, Chicago, 61820-6211, USA"],"affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illionois Urbana-Champaign, 501 E. Daniel St. MC-493, Champaign, Chicago, 61820-6211, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116268360","display_name":"Ajiboye Babalola","orcid":null},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ajiboye Babalola","raw_affiliation_strings":["Computational and Data Sciences Department, George Mason Korea, Munhwa-ro 119-4, Incheon, 21985, South Korea"],"affiliations":[{"raw_affiliation_string":"Computational and Data Sciences Department, George Mason Korea, Munhwa-ro 119-4, Incheon, 21985, South Korea","institution_ids":["https://openalex.org/I146429904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077912411","display_name":"Arnout Van Messem","orcid":"https://orcid.org/0000-0001-8545-7437"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Arnout Van Messem","raw_affiliation_strings":["Department of Mathematics, University of Li\u00e8ge, 4000, Li\u00e8ge, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Li\u00e8ge, 4000, Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029555436","display_name":"Wesley De Neve","orcid":"https://orcid.org/0000-0002-8190-3839"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210132857","display_name":"Ghent University Global Campus","ror":"https://ror.org/041bygf77","country_code":"KR","type":"education","lineage":["https://openalex.org/I32597200","https://openalex.org/I4210132857"]}],"countries":["BE","KR"],"is_corresponding":false,"raw_author_name":"Wesley De Neve","raw_affiliation_strings":["Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Munhwa-ro 119-5, Incheon, 21985, South Korea","Department of Electronics and Information Systems, Ghent University, Technologiepark-Zwijnaarde 126, 9052, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Munhwa-ro 119-5, Incheon, 21985, South Korea","institution_ids":["https://openalex.org/I4210132857"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Technologiepark-Zwijnaarde 126, 9052, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068577161"],"corresponding_institution_ids":["https://openalex.org/I32597200","https://openalex.org/I4210132857"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":10.4495,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97533365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"114","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.994700014591217,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.994700014591217,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9919000267982483,"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":0.9865999817848206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.681073784828186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5548532605171204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5422642230987549},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.47072282433509827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45405465364456177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3211172819137573},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06129568815231323}],"concepts":[{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.681073784828186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5548532605171204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5422642230987549},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.47072282433509827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45405465364456177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3211172819137573},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06129568815231323},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10994-024-06693-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06693-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06693-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/328593","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/328593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Machine Learning, 114 (3) (2025-02-14)","raw_type":"peer reviewed"},{"id":"pmh:oai:archive.ugent.be:01JMVTJPHS3HXEV7WB402R053Z","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JMVTJPHS3HXEV7WB402R053Z","pdf_url":"https://biblio.ugent.be/publication/01JMVTJPHS3HXEV7WB402R053Z/file/01JMVTK4BCA829V6N36RCSNKCE.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 1573-0565","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1007/s10994-024-06693-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06693-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06693-x.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407567451.pdf","grobid_xml":"https://content.openalex.org/works/W4407567451.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W575749427","https://openalex.org/W658722133","https://openalex.org/W2031342017","https://openalex.org/W2073241381","https://openalex.org/W2078734689","https://openalex.org/W2098824882","https://openalex.org/W2108598243","https://openalex.org/W2139577967","https://openalex.org/W2146193817","https://openalex.org/W2155163959","https://openalex.org/W2168458505","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2522957395","https://openalex.org/W2549139847","https://openalex.org/W2602856279","https://openalex.org/W2752782242","https://openalex.org/W2898158860","https://openalex.org/W2962971773","https://openalex.org/W2963351448","https://openalex.org/W2963446712","https://openalex.org/W2963821229","https://openalex.org/W2963995504","https://openalex.org/W2964350391","https://openalex.org/W2979815249","https://openalex.org/W2990138404","https://openalex.org/W2992308087","https://openalex.org/W3001197829","https://openalex.org/W3007260230","https://openalex.org/W3014940504","https://openalex.org/W3156669901","https://openalex.org/W3159481202","https://openalex.org/W3209159014","https://openalex.org/W4214669216","https://openalex.org/W6931259419"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"Neural":[2],"Networks":[3],"(DNNs)":[4],"often":[5],"demonstrate":[6],"remarkable":[7],"performance":[8,48,76,93,162,209,273],"when":[9,25,86,217,249],"evaluated":[10,87,136],"on":[11,49,74,88,143],"the":[12,37,59,67,75,121,130,135,144,184,208,212,237,258],"test":[13,51,69,137],"dataset":[14,104,232,241],"used":[15,64],"during":[16],"model":[17,43,168,199,220,252],"creation.":[18],"However,":[19],"their":[20,147,150,191],"ability":[21],"to":[22,35,45,65,128,177,195,230,257,280],"generalize":[23],"effectively":[24],"deployed":[26],"is":[27,44,126,164,274],"crucial,":[28],"especially":[29,267],"in":[30,82,134,149,207,268],"critical":[31,269],"applications.":[32],"One":[33],"approach":[34],"assess":[36,140],"generalization":[38,101,272],"capability":[39],"of":[40,78,132,146,228,239,260,275],"a":[41,111,204,224],"DNN":[42,80,181,251,265],"evaluate":[46],"its":[47],"replicated":[50,90,192,215],"datasets,":[52],"which":[53],"are":[54],"created":[55],"by":[56,100,120,167],"closely":[57],"following":[58],"same":[60],"methodology":[61],"and":[62,139,186,214,243,263],"procedures":[63],"generate":[66],"original":[68,213],"dataset.":[70],"Our":[71,234],"investigation":[72],"focuses":[73],"degradation":[77,94],"pre-trained":[79,180],"models":[81,122,182,229],"multi-class":[83],"classification":[84],"tasks":[85],"these":[89],"datasets;":[91],"this":[92,154],"has":[95],"not":[96],"been":[97],"entirely":[98],"explained":[99],"shortcomings":[102],"or":[103,170],"disparities.":[105],"To":[106],"address":[107],"this,":[108],"we":[109,156],"introduce":[110],"new":[112],"evaluation":[113,247],"framework":[114,125,176],"that":[115],"leverages":[116],"uncertainty":[117],"estimates":[118],"generated":[119],"studied.":[123],"This":[124,222,254],"designed":[127],"isolate":[129],"impact":[131],"variations":[133],"datasets":[138,216],"DNNs":[141],"based":[142],"consistency":[145],"confidence":[148],"predictions.":[151],"By":[152],"employing":[153],"framework,":[155],"can":[157],"determine":[158],"whether":[159],"an":[160],"observed":[161],"drop":[163],"primarily":[165],"caused":[166],"inadequacy":[169],"other":[171],"factors.":[172],"We":[173],"applied":[174],"our":[175,201,282],"analyze":[178],"564":[179],"across":[183],"CIFAR-10":[185],"ImageNet":[187],"benchmarks,":[188],"along":[189],"with":[190],"versions.":[193],"Contrary":[194],"common":[196],"assumptions":[197],"about":[198],"inadequacy,":[200],"results":[202],"indicate":[203],"substantial":[205],"reduction":[206],"gap":[210],"between":[211],"accounting":[218],"for":[219],"uncertainty.":[221],"suggests":[223],"previously":[225],"unrecognized":[226],"adaptability":[227],"minor":[231],"variations.":[233],"findings":[235],"emphasize":[236],"importance":[238],"understanding":[240],"intricacies":[242],"adopting":[244],"more":[245,261],"nuanced":[246],"methods":[248],"assessing":[250],"performance.":[253],"research":[255],"contributes":[256],"development":[259],"robust":[262],"reliable":[264],"models,":[266],"applications":[270],"where":[271],"utmost":[276],"importance.":[277],"The":[278],"code":[279],"reproduce":[281],"experiments":[283],"will":[284],"be":[285],"available":[286],"at":[287],"https://github.com/esla/Reassessing_DNN_Accuracy":[288],".":[289]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}