{"id":"https://openalex.org/W3015284407","doi":"https://doi.org/10.1109/icassp40776.2020.9053605","title":"Corrdrop: Correlation Based Dropout for Convolutional Neural Networks","display_name":"Corrdrop: Correlation Based Dropout for Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015284407","doi":"https://doi.org/10.1109/icassp40776.2020.9053605","mag":"3015284407"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5076901150","display_name":"Yuyuan Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuyuan Zeng","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023762528","display_name":"Tao Dai","orcid":"https://orcid.org/0000-0003-0594-6404"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Dai","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034104790","display_name":"Shu\u2010Tao Xia","orcid":"https://orcid.org/0000-0002-8639-982X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu-Tao Xia","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076901150"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5862,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68037911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3742","last_page":"3746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9984999895095825,"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":0.996999979019165,"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/dropout","display_name":"Dropout (neural networks)","score":0.9213071465492249},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7947680950164795},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.731874942779541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.72154700756073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7047129273414612},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7030366063117981},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6937692165374756},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.6438300609588623},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4148361086845398},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40537288784980774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24773195385932922},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20877724885940552}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.9213071465492249},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7947680950164795},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.731874942779541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72154700756073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7047129273414612},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7030366063117981},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6937692165374756},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.6438300609588623},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4148361086845398},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40537288784980774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24773195385932922},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20877724885940552},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W104184427","https://openalex.org/W639708223","https://openalex.org/W1563795667","https://openalex.org/W1686810756","https://openalex.org/W1936750108","https://openalex.org/W2016043834","https://openalex.org/W2095705004","https://openalex.org/W2144513243","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2331143823","https://openalex.org/W2401231614","https://openalex.org/W2561238782","https://openalex.org/W2613718673","https://openalex.org/W2746314669","https://openalex.org/W2804047946","https://openalex.org/W2890166761","https://openalex.org/W2950557962","https://openalex.org/W2952634764","https://openalex.org/W2963150697","https://openalex.org/W2963403868","https://openalex.org/W2963495494","https://openalex.org/W2963938169","https://openalex.org/W2964081807","https://openalex.org/W2964137095","https://openalex.org/W2998508940","https://openalex.org/W3118608800","https://openalex.org/W4295727797","https://openalex.org/W4385245566","https://openalex.org/W6600213771","https://openalex.org/W6604254268","https://openalex.org/W6620707391","https://openalex.org/W6633802082","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6681151457","https://openalex.org/W6684191040","https://openalex.org/W6730179637","https://openalex.org/W6739901393","https://openalex.org/W6743428213","https://openalex.org/W6751795773","https://openalex.org/W6754484989","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2761785940","https://openalex.org/W2952813363","https://openalex.org/W4360783045","https://openalex.org/W2129933262","https://openalex.org/W2963346891","https://openalex.org/W3176438653","https://openalex.org/W2770149305","https://openalex.org/W3167930666","https://openalex.org/W3014952856","https://openalex.org/W3010730661"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"can":[4,137],"be":[5],"easily":[6],"over-fitted":[7],"when":[8],"they":[9],"are":[10],"over-parametered.":[11],"The":[12],"popular":[13],"dropout":[14,38,81],"that":[15,52],"drops":[16],"feature":[17,54,92,96,104,120],"units":[18,55,93],"randomly":[19],"can't":[20],"always":[21],"work":[22],"well":[23,140],"for":[24],"CNNs,":[25],"due":[26],"to":[27,68,87],"the":[28,62,100,107,116,119,134,153],"problem":[29],"of":[30,64,70,144,155],"under-dropping.":[31],"To":[32,72],"eliminate":[33],"this":[34],"problem,":[35],"some":[36],"structural":[37,80],"methods":[39,51],"such":[40],"as":[41],"SpatialDropout,":[42],"Cutout":[43],"and":[44,122],"DropBlock":[45],"have":[46,61],"been":[47],"proposed.":[48],"However,":[49],"these":[50,74],"drop":[53],"in":[56,103,118],"continuous":[57],"regions":[58,128],"randomly,":[59],"may":[60],"risk":[63],"over-dropping,":[65],"thus":[66],"leading":[67],"degradation":[69],"performance.":[71],"address":[73],"issues,":[75],"we":[76],"propose":[77],"a":[78],"novel":[79],"method,":[82],"Correlation":[83],"based":[84,94,114],"Dropout":[85],"(CorrDrop),":[86],"regularize":[88,138],"CNNs":[89,139],"by":[90,141],"dropping":[91],"on":[95,115,149],"correlation,":[97],"which":[98],"reflects":[99],"discriminative":[101],"information":[102],"maps.":[105],"Specifically,":[106],"proposed":[108,135],"method":[109,136,157],"first":[110],"obtains":[111],"correlation":[112],"map":[113],"activation":[117],"maps,":[121],"then":[123],"adaptively":[124],"masks":[125],"out":[126],"those":[127],"with":[129,159],"small":[130],"average":[131],"correlation.":[132],"Thus,":[133],"discarding":[142],"part":[143],"contextual":[145],"regions.":[146],"Extensive":[147],"experiments":[148],"image":[150],"classification":[151],"demonstrate":[152],"superiority":[154],"our":[156],"compared":[158],"other":[160],"counterparts.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}