{"id":"https://openalex.org/W3199929490","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534331","title":"Optimized Computation Combining Classification and Detection Networks with Distillation","display_name":"Optimized Computation Combining Classification and Detection Networks with Distillation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199929490","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534331","mag":"3199929490"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74577","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100771701","display_name":"Meng Xu","orcid":"https://orcid.org/0000-0003-4857-5439"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Meng Xu","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048871276","display_name":"Yang Gu","orcid":"https://orcid.org/0000-0001-8572-2907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Gu","raw_affiliation_strings":["Momenta Suzhou Momenta, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Momenta Suzhou Momenta, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018639589","display_name":"Stefan Poslad","orcid":"https://orcid.org/0000-0002-3156-9609"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Poslad","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027754945","display_name":"Shiqing Xue","orcid":"https://orcid.org/0000-0003-3935-5549"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqing Xue","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100771701"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11449617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.996999979019165,"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"}},{"id":"https://openalex.org/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7979953289031982},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7887421250343323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5878086090087891},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5812793970108032},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5600519776344299},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.554279625415802},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.539552628993988},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49904942512512207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49008214473724365},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4877777695655823},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4346562623977661},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43324345350265503},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14264985918998718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979953289031982},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7887421250343323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5878086090087891},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5812793970108032},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5600519776344299},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.554279625415802},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.539552628993988},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49904942512512207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49008214473724365},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4877777695655823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4346562623977661},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43324345350265503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14264985918998718},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/74577","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74577","pdf_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74577","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/74577","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74577","pdf_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74577","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5825030676","display_name":null,"funder_award_id":"Ph.D. scholarship","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3199929490.pdf","grobid_xml":"https://content.openalex.org/works/W3199929490.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1932198206","https://openalex.org/W1970696760","https://openalex.org/W2128529555","https://openalex.org/W2279098554","https://openalex.org/W2294370754","https://openalex.org/W2592691248","https://openalex.org/W2613718673","https://openalex.org/W2620998106","https://openalex.org/W2626089772","https://openalex.org/W2738029666","https://openalex.org/W2740520864","https://openalex.org/W2750784772","https://openalex.org/W2756085244","https://openalex.org/W2803023299","https://openalex.org/W2921245078","https://openalex.org/W2953070460","https://openalex.org/W2959289524","https://openalex.org/W2962734330","https://openalex.org/W2963145730","https://openalex.org/W2963225922","https://openalex.org/W2964082701","https://openalex.org/W2964118293","https://openalex.org/W2964222566","https://openalex.org/W2964269434","https://openalex.org/W2996481948","https://openalex.org/W3118608800","https://openalex.org/W3154571917","https://openalex.org/W3170874841","https://openalex.org/W4297790825","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6685891324","https://openalex.org/W6733814495","https://openalex.org/W6739475399","https://openalex.org/W6741502269","https://openalex.org/W6743188669","https://openalex.org/W6744495609","https://openalex.org/W6751751081","https://openalex.org/W6760370003","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4231775656","https://openalex.org/W4321487865","https://openalex.org/W2046435967","https://openalex.org/W4313906399","https://openalex.org/W3026162553","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2969228573","https://openalex.org/W2963690996"],"abstract_inverted_index":{"A":[0],"Convolutional":[1],"neural":[2],"network":[3,78,142,169],"(CNN)":[4],"has":[5],"emerged":[6],"as":[7],"a":[8,56,62,119],"widely":[9],"used":[10],"approach":[11],"to":[12,28,102],"computer":[13],"vision":[14],"tasks,":[15],"including":[16],"object":[17,114,179],"classification":[18,152],"and":[19,36,126,136],"detection":[20,115,168,180],"tasks.":[21],"The":[22],"high":[23],"requirement":[24],"for":[25,131],"the":[26,74,77,82,86,141,147,151,167],"model":[27,47],"be":[29,100,155,172],"more":[30,75],"computationally":[31],"efficient":[32],"on":[33,143],"lower":[34],"information":[35],"communication":[37],"technology":[38],"(ICT)":[39],"resource,":[40],"e.g.,":[41,80],"mobile":[42],"terminals":[43],"can":[44,154],"benefit":[45],"from":[46,55],"distillation.":[48,87],"However,":[49],"most":[50],"existing":[51],"distillation":[52,106,129],"methods":[53],"suffer":[54],"significant":[57],"accuracy":[58,153],"reduction,":[59],"which":[60,117],"requires":[61],"large":[63],"number":[64],"of":[65,73,76],"pre-training":[66],"models":[67,104],"or":[68],"doesn't":[69],"make":[70],"good":[71],"use":[72],"information,":[79],"in":[81],"middle":[83],"layers,":[84],"during":[85],"In":[88],"this":[89],"paper,":[90],"we":[91],"study":[92],"how":[93],"knowledge":[94],"about":[95,161],"traffic":[96],"signs":[97],"recognition":[98],"could":[99,171],"transferred":[101],"smaller":[103],"by":[105,157,174],"while":[107,166],"cutting":[108],"channels.":[109],"We":[110,139],"present":[111],"an":[112,177],"optimized":[113,178],"network,":[116],"uses":[118],"Region":[120],"Proposal":[121],"Network":[122],"(RPN)":[123],"weighted":[124],"loss":[125,130],"hard-soft":[127],"distribution-wise":[128],"structural":[132],"differences":[133],"between":[134],"teacher":[135],"student":[137],"networks.":[138],"validate":[140],"multiple":[144],"real-world":[145],"datasets,":[146],"experiments":[148],"demonstrate":[149],"that":[150],"improved":[156],"9":[158],"%":[159],"with":[160],"16":[162],"times":[163],"parameter":[164],"reduction":[165],"performance":[170],"increased":[173],"10.6%":[175],"using":[176],"network.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}