{"id":"https://openalex.org/W2891287491","doi":"https://doi.org/10.1109/icpr.2018.8545612","title":"Rethinking ReLU to Train Better CNNs","display_name":"Rethinking ReLU to Train Better CNNs","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2891287491","doi":"https://doi.org/10.1109/icpr.2018.8545612","mag":"2891287491"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2018.8545612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","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/A5073574475","display_name":"Gangming Zhao","orcid":"https://orcid.org/0000-0001-8441-5462"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gangming Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028016065","display_name":"Zhaoxiang Zhang","orcid":"https://orcid.org/0000-0003-2648-3875"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxiang Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112203217","display_name":"He Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Guan","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101630526","display_name":"Peng Tang","orcid":"https://orcid.org/0000-0001-5830-6377"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Tang","raw_affiliation_strings":["School of EIC, Huazhong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075880303","display_name":"Jingdong Wang","orcid":"https://orcid.org/0000-0002-4888-4445"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jingdong Wang","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073574475"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.5669,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.87845637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"603","last_page":"608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10320","display_name":"Neural Networks and Applications","score":0.9991000294685364,"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/T12676","display_name":"Machine Learning and ELM","score":0.9990000128746033,"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/convolution","display_name":"Convolution (computer science)","score":0.7908724546432495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7789974212646484},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7696532011032104},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7062428593635559},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5580887198448181},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47436174750328064},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4372548460960388},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4245986342430115},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.4205373227596283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39435356855392456},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3497103452682495},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33057376742362976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1580767035484314},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06060546636581421}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7908724546432495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789974212646484},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7696532011032104},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7062428593635559},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5580887198448181},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47436174750328064},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4372548460960388},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4245986342430115},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.4205373227596283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39435356855392456},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3497103452682495},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33057376742362976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1580767035484314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06060546636581421},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/icpr.2018.8545612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1849277567","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2156387975","https://openalex.org/W2163605009","https://openalex.org/W2176412452","https://openalex.org/W2194775991","https://openalex.org/W2300805302","https://openalex.org/W2302255633","https://openalex.org/W2523728418","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2552488921","https://openalex.org/W2748788739","https://openalex.org/W2772757469","https://openalex.org/W2962685937","https://openalex.org/W2962835968","https://openalex.org/W2963019788","https://openalex.org/W2963173190","https://openalex.org/W2963285578","https://openalex.org/W2964137095","https://openalex.org/W2964227312","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6639204139","https://openalex.org/W6648737282","https://openalex.org/W6674330103","https://openalex.org/W6684191040","https://openalex.org/W6698183232","https://openalex.org/W6713132643","https://openalex.org/W6746661246"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W2766634277","https://openalex.org/W2755240195","https://openalex.org/W2899217644","https://openalex.org/W2561485601","https://openalex.org/W3015279089","https://openalex.org/W4312551941","https://openalex.org/W3080226283","https://openalex.org/W3045877795","https://openalex.org/W4294069551"],"abstract_inverted_index":{"Most":[0],"of":[1,140],"convolutional":[2,10],"neural":[3],"networks":[4,108],"share":[5],"the":[6,25,35,39,49,57,76,88,116,123,138],"same":[7],"characteristic:":[8],"each":[9],"layer":[11,18],"is":[12,24],"followed":[13],"by":[14],"a":[15,66,83],"nonlinear":[16],"activation":[17],"where":[19],"Rectified":[20],"Linear":[21],"Unit":[22],"(ReLU)":[23],"most":[26],"widely":[27],"used.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,62,81],"argue":[33],"that":[34,122],"designed":[36],"structure":[37],"with":[38,109,132],"equal":[40],"ratio":[41,89],"between":[42,90],"these":[43],"two":[44],"layers":[45],"may":[46],"not":[47],"be":[48,96,103],"best":[50],"choice":[51],"since":[52],"it":[53],"could":[54],"result":[55],"in":[56,105],"poor":[58],"generalization":[59],"ability.":[60],"Thus,":[61],"try":[63],"to":[64,74,86,95,114],"investigate":[65],"more":[67],"suitable":[68],"method":[69,125],"on":[70,129],"using":[71],"ReL":[72],"U":[73],"explore":[75],"better":[77,127],"network":[78,134],"architectures.":[79],"Specifically,":[80],"propose":[82],"proportional":[84,100],"module":[85,101],"keep":[87],"convolution":[91],"and":[92],"ReLU":[93],"amount":[94],"N:m":[97],"(n>m).":[98],"The":[99],"can":[102],"applied":[104],"almost":[106],"all":[107],"no":[110],"extra":[111],"computational":[112],"cost":[113],"improve":[115],"performance.":[117],"Comprehensive":[118],"experimental":[119],"results":[120],"indicate":[121],"proposed":[124],"achieves":[126],"performance":[128],"different":[130,133],"benchmarks":[131],"architectures,":[135],"thus":[136],"verify":[137],"superiority":[139],"our":[141],"work.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}