{"id":"https://openalex.org/W2902974411","doi":"https://doi.org/10.1109/icpr.2018.8545587","title":"Accelerating the Classification of Very Deep Convolutional Network by A Cascading Approach","display_name":"Accelerating the Classification of Very Deep Convolutional Network by A Cascading Approach","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2902974411","doi":"https://doi.org/10.1109/icpr.2018.8545587","mag":"2902974411"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2018.8545587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545587","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":"conference-paper","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/A5101590595","display_name":"Zheng Wu","orcid":"https://orcid.org/0000-0001-7147-173X"},"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":"Wu Zheng","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"96","issue":null,"first_page":"355","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.7582648992538452},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6235693693161011},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.60910964012146},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5980859398841858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5710981488227844},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5381650924682617},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44934096932411194},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43841418623924255},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.43406885862350464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41412675380706787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35645389556884766},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3225136995315552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14737221598625183},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0702211856842041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582648992538452},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6235693693161011},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.60910964012146},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5980859398841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710981488227844},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5381650924682617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44934096932411194},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43841418623924255},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.43406885862350464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41412675380706787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35645389556884766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3225136995315552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14737221598625183},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0702211856842041},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2018.8545587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545587","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1799366690","https://openalex.org/W1905692714","https://openalex.org/W1988790447","https://openalex.org/W2031489346","https://openalex.org/W2051131492","https://openalex.org/W2093717447","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2112076978","https://openalex.org/W2163605009","https://openalex.org/W2168894214","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2963446712","https://openalex.org/W2963606038","https://openalex.org/W3004732066","https://openalex.org/W3118608800","https://openalex.org/W4248437541","https://openalex.org/W6676769703","https://openalex.org/W6684191040","https://openalex.org/W6684665197","https://openalex.org/W6698183232"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W4293226380","https://openalex.org/W2788972299","https://openalex.org/W2359776416","https://openalex.org/W2521347458","https://openalex.org/W2498789492","https://openalex.org/W2353788488","https://openalex.org/W2729981612","https://openalex.org/W4233449973"],"abstract_inverted_index":{"Large":[0],"convolutional":[1,13,58],"networks":[2,73,91,106,116,143],"have":[3],"achieved":[4],"impressive":[5],"classification":[6,40,54,130],"performances":[7],"recently.":[8],"To":[9,42],"achieve":[10],"better":[11],"performance,":[12],"network":[14,24],"tends":[15],"to":[16,38,51,66,88,103,133,158,182,199],"develop":[17],"into":[18],"deeper.":[19],"However,":[20],"the":[21,27,39,53,63,68,75,84,89,94,99,104,109,113,121,129,134,139,151,155,159,162,174,188,193,200],"increase":[22,37],"of":[23,30,55,71,120,144,153],"depth":[25],"causes":[26],"linear":[28],"growth":[29],"computational":[31,95],"complexity,":[32,96],"but":[33],"cannot":[34],"bring":[35],"equivalent":[36],"accuracy.":[41],"alleviate":[43],"this":[44],"inconsistence,":[45],"we":[46,81],"propose":[47],"a":[48],"cascading":[49],"approach":[50],"accelerate":[52],"very":[56,201],"deep":[57,105,202],"neural":[59],"network.":[60,136],"By":[61],"exploiting":[62],"entropy":[64],"metric":[65],"analyze":[67],"statistic":[69],"differences":[70],"basic":[72],"between":[74,123],"correctly":[76],"and":[77,97,169,179,184],"mistakenly":[78],"classified":[79,101],"images,":[80],"can":[82,117,172,191],"assign":[83],"easily":[85],"distinguished":[86],"images":[87,102],"shallow":[90],"for":[92,107],"reducing":[93],"leave":[98],"difficultly":[100],"maintaining":[108],"overall":[110],"performance.":[111],"Besides,":[112],"proposed":[114],"cascaded":[115,167,170,189],"take":[118],"advantage":[119],"complementarity":[122],"different":[124,145],"networks,":[125],"which":[126],"may":[127],"boost":[128],"accuracy":[131,157],"compared":[132,181,198],"deepest":[135,160],"We":[137],"perform":[138],"experiments":[140],"using":[141],"residual":[142],"depths":[146],"on":[147,150],"cifar100":[148],"dataset,":[149],"condition":[152],"obtaining":[154],"similar":[156],"network,":[161],"results":[163],"show":[164],"that":[165],"our":[166],"ResNet32-ResNet110":[168],"ResNet32-ResNet164":[171],"reduce":[173,192],"computation":[175,194],"time":[176,195],"by":[177,196],"48.6%":[178],"44.3%":[180],"ResNet110":[183],"ResNet164,":[185],"respectively.":[186],"And":[187],"ResNet32-ResNet110-ResNet164":[190],"85.4%":[197],"Resnet1001.":[203]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}