{"id":"https://openalex.org/W3045276399","doi":"https://doi.org/10.1109/icpr48806.2021.9412733","title":"MaxDropout: Deep Neural Network Regularization Based on Maximum Output Values","display_name":"MaxDropout: Deep Neural Network Regularization Based on Maximum Output Values","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3045276399","doi":"https://doi.org/10.1109/icpr48806.2021.9412733","mag":"3045276399"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412733","doi":"https://doi.org/10.1109/icpr48806.2021.9412733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412733","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"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/A5005758978","display_name":"Claudio Filipi Goncalves do Santos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Claudio Filipi Goncalves do Santos","raw_affiliation_strings":["Federal University of Sao Carlos - UFSCar, Brazil","Federal University of S\u00e3o Carlos;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Sao Carlos - UFSCar, Brazil","institution_ids":["https://openalex.org/I177909021"]},{"raw_affiliation_string":"Federal University of S\u00e3o Carlos;","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016083289","display_name":"Danilo Colombo","orcid":"https://orcid.org/0000-0003-3851-6718","observed_orcids":["https://orcid.org/0000-0003-3851-6718","https://orcid.org/0000-0001-5832-7573"]},"institutions":[{"id":"https://openalex.org/I32393484","display_name":"Petrobras (Brazil)","ror":"https://ror.org/0235kyq22","country_code":"BR","type":"company","lineage":["https://openalex.org/I32393484"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Danilo Colombo","raw_affiliation_strings":["Petr\u00f3leo Brasileiro - Petrobras","Petrobras,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Petr\u00f3leo Brasileiro - Petrobras","institution_ids":["https://openalex.org/I32393484"]},{"raw_affiliation_string":"Petrobras,","institution_ids":["https://openalex.org/I32393484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035837692","display_name":"Mateus Roder","orcid":"https://orcid.org/0000-0002-3112-5290","observed_orcids":["https://orcid.org/0000-0002-3112-5290"]},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Mateus Roder","raw_affiliation_strings":["S\u00e3o Paulo State University - UNESP, Brazil","Sao Paulo State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S\u00e3o Paulo State University - UNESP, Brazil","institution_ids":["https://openalex.org/I879563668"]},{"raw_affiliation_string":"Sao Paulo State University","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003275797","display_name":"Jo\u00e3o Paulo Papa","orcid":"https://orcid.org/0000-0002-6494-7514","observed_orcids":["https://orcid.org/0000-0002-6494-7514"]},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Joao Paulo Papa","raw_affiliation_strings":["S\u00e3o Paulo State University - UNESP, Brazil","Sao Paulo State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S\u00e3o Paulo State University - UNESP, Brazil","institution_ids":["https://openalex.org/I879563668"]},{"raw_affiliation_string":"Sao Paulo State University","institution_ids":["https://openalex.org/I879563668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2401,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.86449618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2671","last_page":"2676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8939999938011169,"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":0.8939999938011169,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.03200000151991844,"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/T10320","display_name":"Neural Networks and Applications","score":0.03009999915957451,"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/neural-network-regularization","display_name":"neural network regularization","score":0.9039999842643738},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.7229999899864197},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.7289999723434448},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.6389999985694885}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9450379610061646},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.8327780365943909},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7470856308937073},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7250050902366638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073752880096436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.69340580701828},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6629660725593567},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6628032922744751},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.659307062625885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4954620599746704},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.47719085216522217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36929887533187866},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412733","doi":"https://doi.org/10.1109/icpr48806.2021.9412733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412733","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1000766763","display_name":null,"funder_award_id":"2017/ 00285-6","funder_id":"https://openalex.org/F4320322468","funder_display_name":"Petrobras"},{"id":"https://openalex.org/G2744736720","display_name":"CeMEAI - Center for Mathematical Sciences Applied to Industry","funder_award_id":"13/07375-0","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G3454416795","display_name":null,"funder_award_id":"#307066/2017-7,#427968/2018-6","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322468","display_name":"Petrobras","ror":"https://ror.org/0235kyq22"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W35527955","https://openalex.org/W1826234144","https://openalex.org/W1836465849","https://openalex.org/W2095705004","https://openalex.org/W2113325037","https://openalex.org/W2155394491","https://openalex.org/W2302255633","https://openalex.org/W2508457857","https://openalex.org/W2560696501","https://openalex.org/W2582745083","https://openalex.org/W2609743871","https://openalex.org/W2746314669","https://openalex.org/W2752013927","https://openalex.org/W2752225195","https://openalex.org/W2770198335","https://openalex.org/W2946948417","https://openalex.org/W2949117887","https://openalex.org/W2951595529","https://openalex.org/W2964137095","https://openalex.org/W2998508940","https://openalex.org/W3118608800","https://openalex.org/W6743806954"],"related_works":["https://openalex.org/W4226139016","https://openalex.org/W3131865653","https://openalex.org/W2610880400","https://openalex.org/W3159798903","https://openalex.org/W2770949156","https://openalex.org/W6968278917","https://openalex.org/W4384666235","https://openalex.org/W6967939112","https://openalex.org/W3180689527","https://openalex.org/W1652178237"],"abstract_inverted_index":{"Different":[0],"techniques":[1],"have":[2,45],"emerged":[3],"in":[4,69,83,119,133],"the":[5,37,77,102,149,159],"deep":[6,63],"learning":[7],"scenario,":[8],"such":[9,142],"as":[10,143],"Convolutional":[11],"Neural":[12],"Networks,":[13,16,21],"Deep":[14],"Belief":[15],"and":[17,115,145],"Long":[18],"Short-Term":[19],"Memory":[20],"to":[22,32,93,110,139],"cite":[23],"a":[24,55,60,70],"few.":[25],"In":[26,50],"lockstep,":[27],"regularization":[28],"methods,":[29],"which":[30],"aim":[31],"prevent":[33],"overfitting":[34],"by":[35,73,126,157,162],"penalizing":[36],"weight":[38],"connections,":[39],"or":[40],"turning":[41],"off":[42],"some":[43],"units,":[44],"been":[46],"widely":[47],"studied":[48],"either.":[49],"this":[51],"paper,":[52],"we":[53,104],"present":[54],"novel":[56],"approach":[57],"called":[58],"MaxDropout,":[59],"regularizer":[61],"for":[62],"neural":[64,113,120,152],"network":[65],"models":[66],"that":[67,106,154],"works":[68],"supervised":[71],"fashion":[72],"removing":[74],"(shutting":[75],"off)":[76],"prominent":[78],"neurons":[79],"(i.e.,":[80],"most":[81],"active)":[82],"each":[84],"hidden":[85],"layer.":[86],"The":[87,128],"model":[88],"forces":[89],"fewer":[90],"activated":[91],"units":[92],"learn":[94],"more":[95],"representative":[96],"information,":[97],"thus":[98],"providing":[99],"sparsity.":[100],"Regarding":[101],"experiments,":[103],"show":[105],"it":[107],"is":[108,124],"possible":[109],"improve":[111],"existing":[112,140,160],"networks":[114,121,153],"provide":[116],"better":[117],"results":[118,138],"when":[122],"Dropout":[123,156],"replaced":[125],"MaxDropout.":[127,163],"proposed":[129],"method":[130],"was":[131],"evaluated":[132],"image":[134],"classification,":[135],"achieving":[136],"comparable":[137],"regularizers,":[141],"Cutout":[144],"RandomErasing,":[146],"also":[147],"improving":[148],"accuracy":[150],"of":[151],"uses":[155],"replacing":[158],"layer":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-07-29T00:00:00"}