{"id":"https://openalex.org/W4385245106","doi":"https://doi.org/10.1109/iscas46773.2023.10181631","title":"RepSGD: Channel Pruning Using Reparamerization for Accelerating Convolutional Neural Networks","display_name":"RepSGD: Channel Pruning Using Reparamerization for Accelerating Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-05-21","ids":{"openalex":"https://openalex.org/W4385245106","doi":"https://doi.org/10.1109/iscas46773.2023.10181631"},"language":"en","primary_location":{"id":"doi:10.1109/iscas46773.2023.10181631","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas46773.2023.10181631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5110741547","display_name":"Nam Joon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Nam Joon Kim","raw_affiliation_strings":["Seoul National University of Science and Technology,Department of Electrical and Information Engineering and Research Center for Electrical and Information Technology,Seoul,Korea,01811"],"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology,Department of Electrical and Information Engineering and Research Center for Electrical and Information Technology,Seoul,Korea,01811","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371185","display_name":"Hyun Kim","orcid":"https://orcid.org/0000-0002-7962-657X"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun Kim","raw_affiliation_strings":["Seoul National University of Science and Technology,Department of Electrical and Information Engineering and Research Center for Electrical and Information Technology,Seoul,Korea,01811"],"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology,Department of Electrical and Information Engineering and Research Center for Electrical and Information Technology,Seoul,Korea,01811","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110741547"],"corresponding_institution_ids":["https://openalex.org/I118373667"],"apc_list":null,"apc_paid":null,"fwci":0.1235,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3957237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"5"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9987000226974487,"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":0.998199999332428,"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/redundancy","display_name":"Redundancy (engineering)","score":0.7622677087783813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7443931102752686},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7037123441696167},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6831796765327454},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4989583492279053},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4804203510284424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46680620312690735},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.45190539956092834},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.438226580619812},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4360814094543457},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.43440505862236023},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.42147254943847656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3849828243255615},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3631879985332489},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10809531807899475}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7622677087783813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443931102752686},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7037123441696167},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6831796765327454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4989583492279053},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4804203510284424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46680620312690735},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.45190539956092834},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.438226580619812},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4360814094543457},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.43440505862236023},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.42147254943847656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3849828243255615},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3631879985332489},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10809531807899475},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas46773.2023.10181631","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas46773.2023.10181631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1072078819","display_name":null,"funder_award_id":"IITP-2023-RS-2022-00156295","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2800371094","https://openalex.org/W2805003733","https://openalex.org/W2808168148","https://openalex.org/W2886851211","https://openalex.org/W2928560789","https://openalex.org/W2935524202","https://openalex.org/W2948253213","https://openalex.org/W2951104886","https://openalex.org/W2962851801","https://openalex.org/W2963150697","https://openalex.org/W2965862774","https://openalex.org/W2971275988","https://openalex.org/W2976540144","https://openalex.org/W2981958729","https://openalex.org/W2993182889","https://openalex.org/W3019048729","https://openalex.org/W3034513523","https://openalex.org/W3035467254","https://openalex.org/W3046669193","https://openalex.org/W3118608800","https://openalex.org/W3159318088","https://openalex.org/W3173390350","https://openalex.org/W3181161645","https://openalex.org/W4285059684","https://openalex.org/W4293584584","https://openalex.org/W4293858361","https://openalex.org/W4312914306","https://openalex.org/W6750227808","https://openalex.org/W6751979845","https://openalex.org/W6752515464","https://openalex.org/W6763591946","https://openalex.org/W6767534822","https://openalex.org/W6779249178","https://openalex.org/W6783970114"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2964954556"],"abstract_inverted_index":{"Channel":[0],"pruning":[1,19,211],"is":[2,71,177,182],"a":[3,61,100],"popular":[4],"method":[5],"for":[6],"compressing":[7],"convolutional":[8],"neural":[9],"networks":[10],"(CNNs)":[11],"while":[12],"maintaining":[13],"acceptable":[14],"accuracy.":[15],"Most":[16],"existing":[17,37,107,210],"channel":[18],"methods":[20,39,58,212],"use":[21,60],"the":[22,34,74,80,106,126,130,137,153,157,168,172,192,198,202],"approach":[23],"of":[24,36,40,171,201],"zeroing":[25],"unnecessary":[26],"filters":[27,49,66,127,155],"and":[28,45,68,96,180,216],"then":[29,46],"removing":[30,47],"them.":[31],"To":[32,83],"address":[33],"limitations":[35],"approaches,":[38],"creating":[41],"forcibly":[42],"filter":[43,121],"redundancy":[44,122],"redundant":[48,154],"have":[50],"been":[51],"proposed":[52],"without":[53],"heuristic":[54],"knowledge.":[55],"However,":[56],"these":[57,85],"also":[59],"deformed":[62],"gradient":[63,194],"to":[64,119,124,184],"make":[65,125],"identical,":[67],"performance":[69],"degradation":[70],"inevitable":[72],"because":[73],"parameters":[75],"cannot":[76],"be":[77],"updated":[78],"using":[79,136,191],"original":[81,138,169,193],"gradients.":[82],"solve":[84],"problems,":[86],"this":[87],"study":[88],"proposes":[89],"RepSGD,":[90],"which":[91],"can":[92],"compress":[93],"CNNs":[94,203],"simply":[95],"efficiently.":[97],"RepSGD":[98,142,164,196,208],"inserts":[99],"new":[101,113],"point-wise":[102,114],"convolution":[103,109,115,132,146,150,159],"layer":[104,160],"after":[105],"standard":[108,131],"layer.":[110,151],"Subsequently,":[111,152],"only":[112],"layers":[116,133,147],"are":[117,134,161],"trained":[118,135],"produce":[120],"(i.e.,":[123],"identical),":[128],"whereas":[129],"gradient.":[139],"After":[140],"training,":[141],"merges":[143],"two":[144],"consecutive":[145],"into":[148],"one":[149],"in":[156,195,213],"merged":[158],"pruned.":[162],"Because":[163],"does":[165],"not":[166,178],"change":[167],"architecture":[170],"CNN,":[173],"additional":[174],"inference":[175],"computation":[176],"required,":[179],"it":[181],"possible":[183],"support":[185],"training":[186],"from":[187],"scratch.":[188],"In":[189],"addition,":[190],"optimizes":[197],"objective":[199],"function":[200],"better.":[204],"We":[205],"show":[206],"that":[207],"outperforms":[209],"various":[214],"models":[215],"datasets":[217],"through":[218],"extensive":[219],"experiments.":[220]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}