{"id":"https://openalex.org/W2914666366","doi":"https://doi.org/10.48550/arxiv.1901.11409","title":"Semantic Redundancies in Image-Classification Datasets: The 10% You Don't Need","display_name":"Semantic Redundancies in Image-Classification Datasets: The 10% You Don't Need","publication_year":2019,"publication_date":"2019-01-29","ids":{"openalex":"https://openalex.org/W2914666366","doi":"https://doi.org/10.48550/arxiv.1901.11409","mag":"2914666366"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1901.11409","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.11409","pdf_url":"https://arxiv.org/pdf/1901.11409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.11409","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076825006","display_name":"Vighnesh Birodkar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Birodkar, Vighnesh","raw_affiliation_strings":["Google Research , Mountain View , CA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research , Mountain View , CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003384169","display_name":"Hossein Mobahi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mobahi, Hossein","raw_affiliation_strings":["Google Research , Mountain View , CA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research , Mountain View , CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017529415","display_name":"Samy Bengio A","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bengio, Samy","raw_affiliation_strings":["Google Research , Mountain View , CA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research , Mountain View , CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":33,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6571999788284302,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6571999788284302,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.24300000071525574,"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":0.09570000320672989,"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/semantic-redundancy","display_name":"semantic redundancy","score":0.7540000081062317},{"id":"https://openalex.org/keywords/image-classification-dataset","display_name":"image classification dataset","score":0.8659999966621399},{"id":"https://openalex.org/keywords/data-subset-selection","display_name":"data subset selection","score":0.5899999737739563},{"id":"https://openalex.org/keywords/object-recognition","display_name":"object recognition","score":0.5659999847412109},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.9309999942779541},{"id":"https://openalex.org/keywords/imagenet","display_name":"ImageNet","score":1.0},{"id":"https://openalex.org/keywords/data-efficiency","display_name":"data efficiency","score":0.7260000109672546},{"id":"https://openalex.org/keywords/training-set-reduction","display_name":"training data reduction","score":0.4690000116825104},{"id":"https://openalex.org/keywords/semantic-correlation","display_name":"semantic correlation","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504746913909912},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5989689230918884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5561093091964722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448768138885498},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4636828303337097},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33182644844055176},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1901.11409","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.11409","pdf_url":"https://arxiv.org/pdf/1901.11409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"mag:2914666366","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1901.11409.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1901.11409","doi":"https://doi.org/10.48550/arxiv.1901.11409","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.11409","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.11409","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.11409","pdf_url":"https://arxiv.org/pdf/1901.11409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W209945127","https://openalex.org/W1644040291","https://openalex.org/W1686810756","https://openalex.org/W1912128066","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2103018059","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2402144811","https://openalex.org/W2518108298","https://openalex.org/W2527569769","https://openalex.org/W2592691248","https://openalex.org/W2605102758","https://openalex.org/W2619184049","https://openalex.org/W2622263826","https://openalex.org/W2752119372","https://openalex.org/W2794302998","https://openalex.org/W2806138827","https://openalex.org/W2901299405","https://openalex.org/W2902142571","https://openalex.org/W2907258563","https://openalex.org/W2909698149","https://openalex.org/W2962804657","https://openalex.org/W2962843773","https://openalex.org/W2963418779","https://openalex.org/W2963446712","https://openalex.org/W3118608800","https://openalex.org/W4288083516"],"related_works":["https://openalex.org/W4382322366","https://openalex.org/W2912218663","https://openalex.org/W4388870456","https://openalex.org/W4212946700","https://openalex.org/W4415182286","https://openalex.org/W3158091537","https://openalex.org/W2947620140","https://openalex.org/W7163667196","https://openalex.org/W4372348283","https://openalex.org/W4412404680"],"abstract_inverted_index":{"Large":[0],"datasets":[1,63,107],"have":[2,30],"been":[3,31],"crucial":[4],"to":[5,34],"the":[6,13,40,45,72,84,95],"success":[7],"of":[8,43,71],"deep":[9],"learning":[10],"models":[11,37],"in":[12,103],"recent":[14],"years,":[15],"which":[16],"keep":[17],"performing":[18],"better":[19,67],"as":[20],"they":[21],"are":[22],"trained":[23,88],"with":[24,83],"more":[25,38,138],"labelled":[26],"data.":[27],"While":[28],"there":[29],"sustained":[32],"efforts":[33],"make":[35],"these":[36],"data-efficient,":[39],"potential":[41],"benefit":[42],"understanding":[44],"data":[46,73],"itself,":[47],"is":[48,94],"largely":[49],"untapped.":[50],"Specifically,":[51],"focusing":[52],"on":[53,81],"object":[54],"recognition":[55],"tasks,":[56],"we":[57,64,112],"wonder":[58],"if":[59],"for":[60,137],"common":[61],"benchmark":[62],"can":[65,79,99,126],"do":[66],"than":[68],"random":[69],"subsets":[70],"and":[74,105,118,134],"find":[75,100],"a":[76],"subset":[77],"that":[78,98,123],"generalize":[80],"par":[82],"full":[85],"dataset":[86],"when":[87],"on.":[89],"To":[90],"our":[91,124],"knowledge,":[92],"this":[93],"first":[96],"result":[97],"notable":[101],"redundancies":[102,133],"CIFAR-10":[104],"ImageNet":[106],"(at":[108],"least":[109],"10%).":[110],"Interestingly,":[111],"observe":[113],"semantic":[114],"correlations":[115],"between":[116],"required":[117],"redundant":[119],"images.":[120],"We":[121],"hope":[122],"findings":[125],"motivate":[127],"further":[128],"research":[129],"into":[130],"identifying":[131],"additional":[132],"exploiting":[135],"them":[136],"efficient":[139],"training":[140],"or":[141],"data-collection.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2019-02-21T00:00:00"}