{"id":"https://openalex.org/W3164560392","doi":"https://doi.org/10.1109/tpami.2021.3136244","title":"AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?","display_name":"AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?","publication_year":2021,"publication_date":"2021-12-17","ids":{"openalex":"https://openalex.org/W3164560392","doi":"https://doi.org/10.1109/tpami.2021.3136244","mag":"3164560392","pmid":"https://pubmed.ncbi.nlm.nih.gov/34919517"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3136244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3136244","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5065550142","display_name":"Weijian Deng","orcid":"https://orcid.org/0000-0003-1565-742X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Weijian Deng","raw_affiliation_strings":["School of Computing, The Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing, The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100709340","display_name":"Liang Zheng","orcid":"https://orcid.org/0000-0002-1464-9500"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liang Zheng","raw_affiliation_strings":["School of Computing, The Australian National University, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing, The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065550142"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":1.1197,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81946332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"46","issue":"3","first_page":"1868","last_page":"1880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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":0.9988999962806702,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9987999796867371,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7420865297317505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7307575345039368},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7256003618240356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.551038920879364},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5151599645614624},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.49229609966278076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47308188676834106},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.46997684240341187},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4460257589817047},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4158391058444977},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1731807291507721},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15190798044204712}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7420865297317505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307575345039368},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7256003618240356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.551038920879364},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5151599645614624},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.49229609966278076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47308188676834106},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.46997684240341187},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4460257589817047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4158391058444977},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1731807291507721},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15190798044204712},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3136244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3136244","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34919517","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34919517","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G1287071976","display_name":null,"funder_award_id":"DE200101283","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":106,"referenced_works":["https://openalex.org/W1565327149","https://openalex.org/W1576445103","https://openalex.org/W1861492603","https://openalex.org/W1917989004","https://openalex.org/W2031489346","https://openalex.org/W2078179989","https://openalex.org/W2099906136","https://openalex.org/W2100659887","https://openalex.org/W2104094955","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2125865219","https://openalex.org/W2151967815","https://openalex.org/W2159291411","https://openalex.org/W2161470549","https://openalex.org/W2335728318","https://openalex.org/W2471188054","https://openalex.org/W2475287302","https://openalex.org/W2522957395","https://openalex.org/W2531327146","https://openalex.org/W2593768305","https://openalex.org/W2746314669","https://openalex.org/W2766897166","https://openalex.org/W2786712888","https://openalex.org/W2798328860","https://openalex.org/W2798381792","https://openalex.org/W2798681837","https://openalex.org/W2867167548","https://openalex.org/W2882999943","https://openalex.org/W2889625178","https://openalex.org/W2900900206","https://openalex.org/W2945655544","https://openalex.org/W2949736877","https://openalex.org/W2963058377","https://openalex.org/W2963236897","https://openalex.org/W2963275094","https://openalex.org/W2963405349","https://openalex.org/W2963739978","https://openalex.org/W2963826681","https://openalex.org/W2963921470","https://openalex.org/W2981720610","https://openalex.org/W2985936292","https://openalex.org/W2992043355","https://openalex.org/W2998351473","https://openalex.org/W2998508940","https://openalex.org/W3005850013","https://openalex.org/W3007625939","https://openalex.org/W3035004544","https://openalex.org/W3035272520","https://openalex.org/W3102616566","https://openalex.org/W3102842772","https://openalex.org/W3107087058","https://openalex.org/W3119635706","https://openalex.org/W3166574225","https://openalex.org/W3175146247","https://openalex.org/W3176732771","https://openalex.org/W3176814451","https://openalex.org/W3177096435","https://openalex.org/W3180332766","https://openalex.org/W3186740887","https://openalex.org/W4214716613","https://openalex.org/W4246659208","https://openalex.org/W4287205383","https://openalex.org/W4297738480","https://openalex.org/W6633949838","https://openalex.org/W6634343353","https://openalex.org/W6636267554","https://openalex.org/W6639480849","https://openalex.org/W6675170660","https://openalex.org/W6681588610","https://openalex.org/W6683633756","https://openalex.org/W6683833458","https://openalex.org/W6703116779","https://openalex.org/W6713955831","https://openalex.org/W6720328385","https://openalex.org/W6728622933","https://openalex.org/W6738201024","https://openalex.org/W6739651123","https://openalex.org/W6740483536","https://openalex.org/W6742630102","https://openalex.org/W6745553787","https://openalex.org/W6745891213","https://openalex.org/W6746171285","https://openalex.org/W6748163547","https://openalex.org/W6748600614","https://openalex.org/W6752049347","https://openalex.org/W6752160200","https://openalex.org/W6752760542","https://openalex.org/W6754995021","https://openalex.org/W6756262388","https://openalex.org/W6757555829","https://openalex.org/W6762745449","https://openalex.org/W6763087592","https://openalex.org/W6764990469","https://openalex.org/W6767228950","https://openalex.org/W6771233102","https://openalex.org/W6771271773","https://openalex.org/W6774457817","https://openalex.org/W6779681340","https://openalex.org/W6780233385","https://openalex.org/W6782157154","https://openalex.org/W6784146242","https://openalex.org/W6784323503","https://openalex.org/W6786798588","https://openalex.org/W6794339910","https://openalex.org/W6796219925"],"related_works":["https://openalex.org/W2391251536","https://openalex.org/W2362198218","https://openalex.org/W1982750869","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2113077220","https://openalex.org/W2375008505","https://openalex.org/W2350679292","https://openalex.org/W2086348228","https://openalex.org/W4390653028"],"abstract_inverted_index":{"Understanding":[0],"model":[1,50],"decision":[2],"under":[3],"novel":[4],"test":[5,20,28,67,147,182],"scenarios":[6,25],"is":[7,15],"central":[8],"to":[9,60,119,137,165],"the":[10,31,96,150,155,177],"community.":[11],"A":[12],"common":[13,32],"practice":[14],"evaluating":[16],"models":[17,131,169],"on":[18,64,95,180],"labeled":[19],"sets.":[21,183],"However,":[22],"many":[23],"real-world":[24],"see":[26],"unlabeled":[27,66],"data,":[29],"rendering":[30],"supervised":[33],"evaluation":[34],"protocols":[35],"infeasible.":[36],"In":[37,149],"this":[38],"paper,":[39],"we":[40,58,128,152],"investigate":[41],"such":[42,87],"an":[43],"important":[44],"but":[45],"under-explored":[46],"problem,":[47],"named":[48],"Automatic":[49],"Evaluation":[51],"(AutoEval).":[52],"Specifically,":[53,127],"given":[54],"a":[55,71,73,103,123,133,146],"trained":[56],"classifier,":[57],"aim":[59],"estimate":[61,138],"its":[62],"accuracy":[63,101,140,179],"various":[65,85,181],"datasets.":[68],"We":[69,184],"construct":[70],"meta-dataset:":[72],"dataset":[74],"comprised":[75],"of":[76,145,176,196],"datasets":[77],"(sample":[78],"sets)":[79],"created":[80],"from":[81,141],"original":[82],"images":[83],"via":[84],"transformations":[86],"as":[88,122],"rotation":[89],"and":[90,159,170,173,192],"background":[91],"substitution.":[92],"Correlation":[93,112],"studies":[94],"meta-dataset":[97,156],"show":[98,153],"that":[99,154],"classifier":[100,139,178],"exhibits":[102],"strong":[104],"negative":[105],"linear":[106],"relationship":[107],"with":[108],"distribution":[109],"shift":[110],"(Pearson's":[111],").":[113],"This":[114],"new":[115],"finding":[116],"inspires":[117],"us":[118,164],"formulate":[120],"AutoEval":[121],"dataset-level":[124],"regression":[125,130,134,168],"problem.":[126],"learn":[129],"(e.g.,":[132],"neural":[135],"network)":[136],"overall":[142],"feature":[143],"statistics":[144],"set.":[148],"experiment,":[151],"contains":[157],"sufficient":[158],"diverse":[160],"sample":[161],"sets,":[162],"allowing":[163],"train":[166],"robust":[167],"report":[171],"reasonable":[172],"promising":[174],"predictions":[175],"also":[185],"provide":[186],"insights":[187],"into":[188],"application":[189],"scopes,":[190],"limitations,":[191],"potential":[193],"future":[194],"directions":[195],"AutoEval.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}