{"id":"https://openalex.org/W3159629309","doi":"https://doi.org/10.1109/icpr48806.2021.9412191","title":"Learning to Prune in Training via Dynamic Channel Propagation","display_name":"Learning to Prune in Training via Dynamic Channel Propagation","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3159629309","doi":"https://doi.org/10.1109/icpr48806.2021.9412191","mag":"3159629309"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412191","pdf_url":null,"source":null,"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"},"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/A5045099798","display_name":"Shibo Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibo Shen","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014842979","display_name":"Rongpeng Li","orcid":"https://orcid.org/0000-0003-4297-5060"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036831868","display_name":"Zhifeng Zhao","orcid":"https://orcid.org/0000-0002-5479-7890"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Zhao","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626771","display_name":"Honggang Zhang","orcid":"https://orcid.org/0000-0001-8287-6783"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Zhang","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020578263","display_name":"Yugeng Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yugeng Zhou","raw_affiliation_strings":["Zhejiang Wanfeng Technology Development Company, Ltd., Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Wanfeng Technology Development Company, Ltd., Zhejiang, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3819,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65480677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"939","last_page":"945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9965999722480774,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9947999715805054,"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":0.8500237464904785},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7175493240356445},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7063403725624084},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.680054783821106},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6796232461929321},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.6694371700286865},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5970968008041382},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5630300045013428},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5249195694923401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4930114448070526},{"id":"https://openalex.org/keywords/propagation-of-uncertainty","display_name":"Propagation of uncertainty","score":0.4698421359062195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4039114713668823},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39543965458869934},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20792388916015625},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16415563225746155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500237464904785},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7175493240356445},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7063403725624084},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.680054783821106},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6796232461929321},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6694371700286865},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5970968008041382},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5630300045013428},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5249195694923401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4930114448070526},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.4698421359062195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4039114713668823},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39543965458869934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20792388916015625},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16415563225746155},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412191","pdf_url":null,"source":null,"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":[],"awards":[{"id":"https://openalex.org/G459520727","display_name":null,"funder_award_id":"61701439,61731002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8870909840","display_name":null,"funder_award_id":"2017YFB1301003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1936750108","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2707890836","https://openalex.org/W2752037867","https://openalex.org/W2808168148","https://openalex.org/W2888421240","https://openalex.org/W2896006880","https://openalex.org/W2896409484","https://openalex.org/W2899771611","https://openalex.org/W2905016238","https://openalex.org/W2928560789","https://openalex.org/W2962835968","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963094099","https://openalex.org/W2963287528","https://openalex.org/W2963363373","https://openalex.org/W2963477586","https://openalex.org/W2963698820","https://openalex.org/W2964233199","https://openalex.org/W2965174861","https://openalex.org/W2971275988","https://openalex.org/W3008935021","https://openalex.org/W3009383973","https://openalex.org/W3118608800","https://openalex.org/W4289243627","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6640494244","https://openalex.org/W6674330103","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6739917289","https://openalex.org/W6743912273","https://openalex.org/W6755034786","https://openalex.org/W6755526309","https://openalex.org/W6755843862","https://openalex.org/W6756040250","https://openalex.org/W6767534822","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W2378211422","https://openalex.org/W4239286941","https://openalex.org/W2088845016","https://openalex.org/W1601203902","https://openalex.org/W2075798043","https://openalex.org/W589102260","https://openalex.org/W4390419160","https://openalex.org/W2102464536"],"abstract_inverted_index":{"In":[0,23],"this":[1],"paper,":[2],"we":[3,25],"propose":[4],"a":[5,28],"novel":[6,114],"network":[7,126],"training":[8,21,44,83,115],"mechanism":[9],"called":[10],"\u201cdynamic":[11],"channel":[12,57],"propagation\u201d":[13],"to":[14,37,47,64],"prune":[15],"the":[16,20,40,48,72,82,137],"neural":[17,107,125],"networks":[18,108],"during":[19],"period.":[22],"particular,":[24],"pick":[26],"up":[27],"specific":[29],"group":[30],"of":[31,51,143],"channels":[32,67,85],"in":[33,39,43],"each":[34],"convolutional":[35,124],"layer":[36],"participate":[38],"forward":[41],"propagation":[42],"time":[45],"according":[46],"significance":[49],"level":[50],"channel,":[52],"which":[53],"is":[54],"defined":[55],"as":[56],"utility.":[58],"The":[59,133],"utility":[60,88,96],"values":[61,89,97],"with":[62,71,86,94],"respect":[63],"all":[65],"selected":[66],"are":[68,90,98],"updated":[69],"simultaneously":[70],"error":[73],"back-propagation":[74],"process":[75],"and":[76,105,122,131,140],"will":[77],"adaptively":[78],"change.":[79],"Furthermore,":[80],"when":[81],"ends,":[84],"high":[87],"retained":[91],"whereas":[92],"those":[93],"low":[95],"discarded.":[99],"Hence,":[100],"our":[101,113,144],"proposed":[102],"scheme":[103,116],"trains":[104],"prunes":[106],"simultaneously.":[109],"We":[110],"empirically":[111],"evaluate":[112],"on":[117],"various":[118],"representative":[119],"benchmark":[120],"datasets":[121],"advanced":[123],"(CNN)":[127],"architectures,":[128],"including":[129],"VGGNet":[130],"ResNet.":[132],"experiment":[134],"results":[135],"verify":[136],"superior":[138],"performance":[139],"robust":[141],"effectiveness":[142],"approach.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}