{"id":"https://openalex.org/W2912218663","doi":"https://doi.org/10.3390/jimaging6060041","title":"Do We Train on Test Data? Purging CIFAR of Near-Duplicates","display_name":"Do We Train on Test Data? Purging CIFAR of Near-Duplicates","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W2912218663","doi":"https://doi.org/10.3390/jimaging6060041","mag":"2912218663","pmid":"https://pubmed.ncbi.nlm.nih.gov/34460587"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging6060041","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging6060041","pdf_url":"https://www.mdpi.com/2313-433X/6/6/41/pdf?version=1592375970","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/6/6/41/pdf?version=1592375970","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bj\u00f6rn Barz","orcid":"https://orcid.org/0000-0003-1019-9538"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bj\u00f6rn Barz","raw_affiliation_strings":["Computer Vision Group, Friedrich Schiller University Jena, Ernst-Abbe-Platz 2, 07743 Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Vision Group, Friedrich Schiller University Jena, Ernst-Abbe-Platz 2, 07743 Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"last","author":{"id":null,"display_name":"Joachim Denzler","orcid":"https://orcid.org/0000-0002-3193-3300"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joachim Denzler","raw_affiliation_strings":["Computer Vision Group, Friedrich Schiller University Jena, Ernst-Abbe-Platz 2, 07743 Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Vision Group, Friedrich Schiller University Jena, Ernst-Abbe-Platz 2, 07743 Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76198965"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":2.4535,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.90793488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"6","issue":"6","first_page":"41","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5562999844551086,"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":0.5562999844551086,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1468999981880188,"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":0.05820000171661377,"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/test-set","display_name":"Test set","score":0.6222000122070312},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5906000137329102},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5674999952316284},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.5609999895095825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5475999712944031},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5063999891281128},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48669999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8532000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7486000061035156},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6222000122070312},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5539000034332275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C180462255","wikidata":"https://www.wikidata.org/wiki/Q3559736","display_name":"Standard test image","level":4,"score":0.41589999198913574},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.40310001373291016},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3390/jimaging6060041","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging6060041","pdf_url":"https://www.mdpi.com/2313-433X/6/6/41/pdf?version=1592375970","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:34460587","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34460587","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":"Journal of imaging","raw_type":null},{"id":"pmh:oai:arXiv.org:1902.00423","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.00423","pdf_url":"https://arxiv.org/pdf/1902.00423","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:oai:doaj.org/article:fb6c68f60d004b8ca92d562365dafef6","is_oa":true,"landing_page_url":"https://doaj.org/article/fb6c68f60d004b8ca92d562365dafef6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 6, Iss 6, p 41 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2313-433X/6/6/41/","is_oa":true,"landing_page_url":"http://doi.org/10.3390/jimaging6060041","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Journal of Imaging","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8321059","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8321059","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging6060041","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging6060041","pdf_url":"https://www.mdpi.com/2313-433X/6/6/41/pdf?version=1592375970","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7523378121","display_name":null,"funder_award_id":"DE 735/11-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2912218663.pdf","grobid_xml":"https://content.openalex.org/works/W2912218663.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W204268067","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2130660124","https://openalex.org/W2145607950","https://openalex.org/W2155803963","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2204975001","https://openalex.org/W2526145926","https://openalex.org/W2549139847","https://openalex.org/W2785430118","https://openalex.org/W2907258563","https://openalex.org/W2962843773","https://openalex.org/W2962971773","https://openalex.org/W2963446712","https://openalex.org/W2990519439","https://openalex.org/W4235505822","https://openalex.org/W6618372016"],"related_works":[],"abstract_inverted_index":{"The":[0,105],"CIFAR-10":[1],"and":[2,16,24,38,63,160,178,183],"CIFAR-100":[3],"datasets":[4,12,49],"are":[5,17,58],"two":[6],"of":[7,30,40,47,69,123,145,157,192],"the":[8,28,41,44,53,67,83,94,102,120,164,168,175,190,193],"most":[9],"heavily":[10],"benchmarked":[11],"in":[13,27,52,93,110,154],"computer":[14],"vision":[15],"often":[18],"used":[19],"to":[20,113,134,141,163],"evaluate":[21],"novel":[22],"methods":[23],"model":[25],"architectures":[26,128],"field":[29],"deep":[31],"learning.":[32],"However,":[33],"we":[34,81,89],"find":[35,150],"that":[36],"3.3%":[37],"10%":[39],"images":[42,99],"from":[43,101],"test":[45,95,132,170],"sets":[46,96,133],"these":[48,130],"have":[50],"duplicates":[51,57,92],"training":[54,106],"set.":[55,171],"These":[56],"easily":[59],"recognizable":[60],"by":[61],"memorization":[62],"may,":[64],"hence,":[65],"bias":[66],"comparison":[68],"image":[70],"recognition":[71],"techniques":[72],"regarding":[73],"their":[74],"generalization":[75],"capability.":[76],"To":[77],"eliminate":[78],"this":[79],"bias,":[80],"provide":[82],"\"fair":[84],"CIFAR\"":[85],"(ciFAIR)":[86],"dataset,":[87],"where":[88],"replaced":[90],"all":[91],"with":[97],"new":[98,131],"sampled":[100],"same":[103],"domain.":[104],"set":[107],"remains":[108],"unchanged,":[109],"order":[111],"not":[112],"invalidate":[114],"pre-trained":[115,179],"models.":[116],"We":[117,149,172],"then":[118],"re-evaluate":[119],"classification":[121,155],"performance":[122,166],"various":[124],"popular":[125],"state-of-the-art":[126],"CNN":[127],"on":[129,167],"investigate":[135],"whether":[136],"recent":[137],"research":[138],"has":[139],"overfitted":[140],"memorizing":[142],"data":[143],"instead":[144],"learning":[146],"abstract":[147],"concepts.":[148],"a":[151,186],"significant":[152],"drop":[153],"accuracy":[156],"between":[158],"9%":[159],"14%":[161],"relative":[162],"original":[165],"duplicate-free":[169],"make":[173],"both":[174],"ciFAIR":[176],"dataset":[177],"models":[180],"publicly":[181],"available":[182],"furthermore":[184],"maintain":[185],"leaderboard":[187],"for":[188],"tracking":[189],"state":[191],"art.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2019-02-21T00:00:00"}