{"id":"https://openalex.org/W3200914073","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533741","title":"Network Pruning via Annealing and Direct Sparsity Control","display_name":"Network Pruning via Annealing and Direct Sparsity Control","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200914073","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533741","mag":"3200914073"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533741","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005966448","display_name":"Yangzi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yangzi Guo","raw_affiliation_strings":["Florida State University, Tallahassee, Florida, USA"],"affiliations":[{"raw_affiliation_string":"Florida State University, Tallahassee, Florida, USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043540428","display_name":"Yiyuan She","orcid":"https://orcid.org/0000-0002-5110-3179"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyuan She","raw_affiliation_strings":["Florida State University, Tallahassee, Florida, USA"],"affiliations":[{"raw_affiliation_string":"Florida State University, Tallahassee, Florida, USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052175239","display_name":"Adrian Barbu","orcid":"https://orcid.org/0000-0002-9548-7872"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrian Barbu","raw_affiliation_strings":["Florida State University, Tallahassee, Florida, USA"],"affiliations":[{"raw_affiliation_string":"Florida State University, Tallahassee, Florida, USA","institution_ids":["https://openalex.org/I103163165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005966448"],"corresponding_institution_ids":["https://openalex.org/I103163165"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39751634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"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":0.9998000264167786,"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":0.9998000264167786,"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/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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7725790739059448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7075051665306091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5985376834869385},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5707124471664429},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.5451400279998779},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.520733118057251},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5003459453582764},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4753187298774719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4096201956272125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3327515423297882},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18259257078170776}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7725790739059448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075051665306091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985376834869385},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5707124471664429},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.5451400279998779},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.520733118057251},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5003459453582764},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4753187298774719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4096201956272125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3327515423297882},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18259257078170776},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533741","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1903029394","https://openalex.org/W2102605133","https://openalex.org/W2112796928","https://openalex.org/W2114766824","https://openalex.org/W2119144962","https://openalex.org/W2125389748","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2335728318","https://openalex.org/W2495425901","https://openalex.org/W2605701576","https://openalex.org/W2613718673","https://openalex.org/W2625838626","https://openalex.org/W2897319353","https://openalex.org/W2949117887","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963145730","https://openalex.org/W2963363373","https://openalex.org/W2963446712","https://openalex.org/W2963674932","https://openalex.org/W2963981420","https://openalex.org/W2964121744","https://openalex.org/W2964299589","https://openalex.org/W2966256598","https://openalex.org/W3118608800","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6677103964","https://openalex.org/W6677580257","https://openalex.org/W6678583879","https://openalex.org/W6684191040","https://openalex.org/W6723181079","https://openalex.org/W6724998850","https://openalex.org/W6725543821","https://openalex.org/W6725739302","https://openalex.org/W6726275242","https://openalex.org/W6739100606"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2373300491","https://openalex.org/W1212596013","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581","https://openalex.org/W4229439743"],"abstract_inverted_index":{"Artificial":[0],"neural":[1,7,33],"networks":[2,8,34],"(ANNs)":[3],"especially":[4],"deep":[5,32],"convolutional":[6],"are":[9],"very":[10],"popular":[11],"these":[12],"days":[13],"and":[14,42,62,85,168],"have":[15],"been":[16],"proved":[17],"to":[18,24,150,183],"successfully":[19],"offer":[20],"quite":[21],"reliable":[22],"solutions":[23],"many":[25],"vision":[26,170],"problems.":[27],"However,":[28],"the":[29,92,98,104,123,135,142,153,158,174],"use":[30],"of":[31,106,122,186],"is":[35,57],"widely":[36],"impeded":[37],"by":[38,73],"their":[39],"intensive":[40],"computational":[41],"memory":[43],"cost.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"a":[50,70,83,86,116],"novel":[51],"efficient":[52],"network":[53,76,93,159,188],"pruning":[54,105,160,189],"framework":[55],"that":[56,91,173],"suitable":[58,102],"for":[59,103],"both":[60],"non-structured":[61],"structured":[63],"channel-level":[64],"pruning.":[65],"Our":[66],"proposed":[67,175],"method":[68,114,176],"tightens":[69],"sparsity":[71,155],"constraint":[72,120,146],"gradually":[74],"removing":[75],"parameters":[77,137],"or":[78,109,138,179],"filter":[79,139],"channels":[80],"based":[81],"on":[82,165],"criterion":[84],"schedule.":[87],"The":[88],"attractive":[89],"fact":[90],"size":[94],"keeps":[95],"dropping":[96],"throughout":[97],"iterations":[99],"makes":[100,147],"it":[101,128,148],"any":[107,132],"untrained":[108],"pre-trained":[110],"network.":[111],"Because":[112],"our":[113],"uses":[115],"<tex":[117,124,143],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[118,125,144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$L_{0}$</tex>":[119,145],"instead":[121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$L_{1}$</tex>":[126],"penalty,":[127],"does":[129],"not":[130],"introduce":[131],"bias":[133],"in":[134],"training":[136],"channels.":[140],"Furthermore,":[141],"easy":[149],"directly":[151],"specify":[152],"desired":[154],"level":[156],"during":[157],"process.":[161],"Finally,":[162],"experimental":[163],"validation":[164],"extensive":[166],"synthetic":[167],"real":[169],"datasets":[171],"show":[172],"obtains":[177],"better":[178],"competitive":[180],"performance":[181],"compared":[182],"other":[184],"states":[185],"art":[187],"methods.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}