{"id":"https://openalex.org/W3013212957","doi":"https://doi.org/10.48550/arxiv.2003.12824","title":"Gradient-based Data Augmentation for Semi-Supervised Learning","display_name":"Gradient-based Data Augmentation for Semi-Supervised Learning","publication_year":2020,"publication_date":"2020-03-28","ids":{"openalex":"https://openalex.org/W3013212957","doi":"https://doi.org/10.48550/arxiv.2003.12824","mag":"3013212957"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2003.12824","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.12824","pdf_url":"https://arxiv.org/pdf/2003.12824","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.12824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060228295","display_name":"Hiroshi Kaizuka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405274107","display_name":"NS Solutions Corporation (Japan)","ror":"https://ror.org/0130sbp19","country_code":"JP","type":"company","lineage":["https://openalex.org/I4405274107"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kaizuka, Hiroshi","raw_affiliation_strings":["NS Solutions Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NS Solutions Corporation","institution_ids":["https://openalex.org/I4405274107"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060228295"],"corresponding_institution_ids":["https://openalex.org/I4405274107"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.6240000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.6240000128746033,"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":0.3093000054359436,"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":0.049400001764297485,"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/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9409999847412109},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.7879999876022339},{"id":"https://openalex.org/keywords/consistency-regularization","display_name":"consistency regularization","score":0.9980000257492065},{"id":"https://openalex.org/keywords/mixup","display_name":"mixup","score":0.9739999771118164},{"id":"https://openalex.org/keywords/dataset-diversity","display_name":"data diversity","score":0.6890000104904175},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.6990000009536743},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.8579999804496765},{"id":"https://openalex.org/keywords/cifar-100","display_name":"CIFAR-100","score":0.9110000133514404},{"id":"https://openalex.org/keywords/svhn","display_name":"SVHN","score":0.9959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572746276855469},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7121430039405823},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.643355131149292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5062574744224548},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4882092773914337},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.48173072934150696},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.472996324300766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46759316325187683},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.46056845784187317},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4302396774291992},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.42578500509262085},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2003.12824","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.12824","pdf_url":"https://arxiv.org/pdf/2003.12824","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":"doi:10.48550/arxiv.2003.12824","doi":"https://doi.org/10.48550/arxiv.2003.12824","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.12824","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:2003.12824","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.12824","pdf_url":"https://arxiv.org/pdf/2003.12824","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3013212957.pdf","grobid_xml":"https://content.openalex.org/works/W3013212957.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2145494108","https://openalex.org/W2157364932","https://openalex.org/W2169393322","https://openalex.org/W2335728318","https://openalex.org/W2530816535","https://openalex.org/W2592691248","https://openalex.org/W2734426634","https://openalex.org/W2746314669","https://openalex.org/W2765407302","https://openalex.org/W2792287754","https://openalex.org/W2794523151","https://openalex.org/W2909869271","https://openalex.org/W2921087533","https://openalex.org/W2942203175","https://openalex.org/W2943865428","https://openalex.org/W2945642819","https://openalex.org/W2949736877","https://openalex.org/W2963207607","https://openalex.org/W2963558289","https://openalex.org/W2963685250","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2964153729","https://openalex.org/W2964159205","https://openalex.org/W2993466051","https://openalex.org/W2994088087","https://openalex.org/W3106031848","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3107606673","https://openalex.org/W4385388771","https://openalex.org/W3210904793","https://openalex.org/W3123204880","https://openalex.org/W3196993835","https://openalex.org/W4293496215","https://openalex.org/W4391997109","https://openalex.org/W2962369866","https://openalex.org/W3087453244","https://openalex.org/W3042190276"],"abstract_inverted_index":{"In":[0],"semi-supervised":[1],"learning":[2],"(SSL),":[3],"a":[4,30,40,141],"technique":[5],"called":[6],"consistency":[7],"regularization":[8],"(CR)":[9],"achieves":[10,148,174],"high":[11,33],"performance.":[12,176],"It":[13],"has":[14,88],"been":[15,89],"proved":[16],"that":[17,48,63,91,132],"the":[18,53,59,65,84,92,129,149,155],"diversity":[19,74],"of":[20,58,81,152],"data":[21,42,73,97,100],"used":[22,134],"in":[23,104,137],"CR":[24,76],"is":[25,49,64,101,126,133],"extremely":[26],"important":[27],"to":[28,70],"obtain":[29],"model":[31,66],"with":[32],"discrimination":[34,121],"performance":[35,122,153,157],"by":[36,77,113,124],"CR.":[37],"We":[38,68,106],"propose":[39,107],"new":[41],"augmentation":[43],"(Gradient-based":[44],"Data":[45],"Augmentation":[46],"(GDA))":[47],"deterministically":[50],"calculated":[51],"from":[52],"image":[54],"pixel":[55],"value":[56],"gradient":[57],"posterior":[60],"probability":[61],"distribution":[62],"output.":[67],"aim":[69],"secure":[71],"effective":[72,103],"for":[75,95,143],"utilizing":[78],"three":[79],"types":[80],"GDA.":[82,119],"On":[83],"other":[85],"hand,":[86],"it":[87],"demonstrated":[90],"mixup":[93,116],"method":[94,110],"labeled":[96],"and":[98,118,166,169],"unlabeled":[99],"also":[102],"SSL.":[105],"an":[108],"SSL":[109,138],"named":[111],"MixGDA":[112,125,147,173],"combining":[114],"various":[115],"methods":[117],"The":[120],"achieved":[123],"evaluated":[127],"against":[128],"13-layer":[130],"CNN":[131],"as":[135,154],"standard":[136],"research.":[139],"As":[140],"result,":[142],"CIFAR-10":[144],"(4000":[145],"labels),":[146,172],"same":[150],"level":[151],"best":[156],"ever":[158],"achieved.":[159],"For":[160],"SVHN":[161],"(250":[162],"labels,":[163],"500":[164],"labels":[165],"1000":[167],"labels)":[168],"CIFAR-100":[170],"(10000":[171],"state-of-the-art":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-04-03T00:00:00"}