{"id":"https://openalex.org/W3023585672","doi":"https://doi.org/10.1109/jstsp.2020.2992390","title":"Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning","display_name":"Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3023585672","doi":"https://doi.org/10.1109/jstsp.2020.2992390","mag":"3023585672"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2020.2992390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2992390","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://purehost.bath.ac.uk/ws/files/211229950/JSTSP_PP_Copy_.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007774595","display_name":"Pravendra Singh","orcid":"https://orcid.org/0000-0003-1001-2219"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Pravendra Singh","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India"],"raw_orcid":"https://orcid.org/0000-0003-1001-2219","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744115","display_name":"Vinay Kumar Verma","orcid":"https://orcid.org/0000-0002-6532-2997"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinay Kumar Verma","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029651089","display_name":"Piyush Rai","orcid":"https://orcid.org/0000-0003-0660-8925"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Piyush Rai","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinay P. Namboodiri","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007774595"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":2.0605,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.89062604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"14","issue":"4","first_page":"838","last_page":"847"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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":0.7659893035888672},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7345673441886902},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6458254456520081},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6418471336364746},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6058710217475891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5443976521492004},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.45755019783973694},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43240344524383545},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42589226365089417},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08180806040763855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659893035888672},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7345673441886902},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6458254456520081},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6418471336364746},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6058710217475891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5443976521492004},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.45755019783973694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43240344524383545},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42589226365089417},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08180806040763855},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jstsp.2020.2992390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2992390","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:purehost.bath.ac.uk:publications/4acd8975-9792-4129-8b35-5254519fd994","is_oa":true,"landing_page_url":"https://researchportal.bath.ac.uk/en/publications/4acd8975-9792-4129-8b35-5254519fd994","pdf_url":"https://purehost.bath.ac.uk/ws/files/211229950/JSTSP_PP_Copy_.pdf","source":{"id":"https://openalex.org/S4377196294","display_name":"Pure (University of Bath)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51601045","host_organization_name":"University of Bath","host_organization_lineage":["https://openalex.org/I51601045"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Singh, P, Verma, V K, Rai, P & Namboodiri, V 2020, 'Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning', IEEE Journal on Selected Topics in Signal Processing, vol. 14, no. 4, 9086749, pp. 838 - 847. https://doi.org/10.1109/JSTSP.2020.2992390","raw_type":"article"},{"id":"pmh:oai:purehost.bath.ac.uk:publications/4acd8975-9792-4129-8b35-5254519fd994","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85089953123&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4377196294","display_name":"Pure (University of Bath)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51601045","host_organization_name":"University of Bath","host_organization_lineage":["https://openalex.org/I51601045"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:purehost.bath.ac.uk:publications/4acd8975-9792-4129-8b35-5254519fd994","is_oa":true,"landing_page_url":"https://researchportal.bath.ac.uk/en/publications/4acd8975-9792-4129-8b35-5254519fd994","pdf_url":"https://purehost.bath.ac.uk/ws/files/211229950/JSTSP_PP_Copy_.pdf","source":{"id":"https://openalex.org/S4377196294","display_name":"Pure (University of Bath)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51601045","host_organization_name":"University of Bath","host_organization_lineage":["https://openalex.org/I51601045"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Singh, P, Verma, V K, Rai, P & Namboodiri, V 2020, 'Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning', IEEE Journal on Selected Topics in Signal Processing, vol. 14, no. 4, 9086749, pp. 838 - 847. https://doi.org/10.1109/JSTSP.2020.2992390","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023585672.pdf","grobid_xml":"https://content.openalex.org/works/W3023585672.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W2002427601","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2119144962","https://openalex.org/W2126333738","https://openalex.org/W2134797427","https://openalex.org/W2194775991","https://openalex.org/W2300242332","https://openalex.org/W2495425901","https://openalex.org/W2520760693","https://openalex.org/W2531409750","https://openalex.org/W2554931888","https://openalex.org/W2565639579","https://openalex.org/W2582745083","https://openalex.org/W2612445135","https://openalex.org/W2613718673","https://openalex.org/W2617991662","https://openalex.org/W2701719801","https://openalex.org/W2707890836","https://openalex.org/W2752037867","https://openalex.org/W2788715907","https://openalex.org/W2807961551","https://openalex.org/W2808168148","https://openalex.org/W2883111419","https://openalex.org/W2886851211","https://openalex.org/W2924515500","https://openalex.org/W2949941638","https://openalex.org/W2952088488","https://openalex.org/W2952432176","https://openalex.org/W2962956675","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963103976","https://openalex.org/W2963117513","https://openalex.org/W2963145730","https://openalex.org/W2963163009","https://openalex.org/W2963287528","https://openalex.org/W2963363373","https://openalex.org/W2963382930","https://openalex.org/W2963674932","https://openalex.org/W2964233199","https://openalex.org/W2964266063","https://openalex.org/W2964299589","https://openalex.org/W2965955046","https://openalex.org/W2968025890","https://openalex.org/W2972565713","https://openalex.org/W3106250896","https://openalex.org/W3118608800","https://openalex.org/W4297775537","https://openalex.org/W4302613003","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6677580257","https://openalex.org/W6679909955","https://openalex.org/W6723181079","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6726973340","https://openalex.org/W6730382033","https://openalex.org/W6732814185","https://openalex.org/W6737664043","https://openalex.org/W6738735913","https://openalex.org/W6739717535","https://openalex.org/W6739917289","https://openalex.org/W6741047420","https://openalex.org/W6743912273","https://openalex.org/W6748570084","https://openalex.org/W6753490951","https://openalex.org/W6785652829","https://openalex.org/W7064683377"],"related_works":["https://openalex.org/W2950475743","https://openalex.org/W4386603768","https://openalex.org/W2886711096","https://openalex.org/W4380078352","https://openalex.org/W3036048022","https://openalex.org/W4309224979","https://openalex.org/W992687842","https://openalex.org/W4300560302","https://openalex.org/W3088108839","https://openalex.org/W3026879719"],"abstract_inverted_index":{"While":[0],"convolutional":[1],"neural":[2],"networks":[3],"(CNNs)":[4],"have":[5],"achieved":[6],"remarkable":[7],"performance":[8],"on":[9],"various":[10],"supervised":[11],"and":[12,84,122,213,215,219,230,273],"unsupervised":[13],"learning":[14],"tasks,":[15],"they":[16],"typically":[17],"consist":[18],"of":[19,23,59,78,103,117,145,152,199,263,265,271,276,283],"a":[20,34,40,70,153],"massive":[21],"number":[22,58,116,262,275],"parameters.":[24],"This":[25],"results":[26],"in":[27,119,143,175],"significant":[28],"memory":[29],"requirements":[30],"as":[31,33,66,225],"well":[32],"computational":[35],"burden.":[36],"Consequently,":[37],"there":[38],"is":[39],"growing":[41],"need":[42],"for":[43,47,74,207],"filter-level":[44,76],"pruning":[45,77,92,110,125,201,290],"approaches":[46],"compressing":[48],"CNN":[49,86],"based":[50],"models":[51,245],"that":[52],"not":[53],"only":[54],"reduce":[55,62,148,171],"the":[56,63,75,96,115,120,132,157,162,168,172,176,194,200,240,261,274],"total":[57],"parameters":[60,264],"but":[61],"overall":[64],"computation":[65],"well.":[67],"We":[68,203,232],"present":[69,234],"new":[71],"min-max":[72],"framework":[73,81,101],"CNNs.":[79],"Our":[80,100,243,258],"jointly":[82],"prunes":[83],"fine-tunes":[85],"model":[87,177],"parameters,":[88],"with":[89,280],"an":[90,268],"adaptive":[91,108],"rate,":[93],"while":[94],"maintaining":[95],"model's":[97],"predictive":[98],"performance.":[99],"consists":[102],"two":[104],"modules:":[105],"(1)":[106],"An":[107],"filter":[109,289],"(AFP)":[111],"module,":[112,129],"which":[113,130],"minimizes":[114],"filters":[118,151,165],"model;":[121],"(2)":[123],"A":[124],"rate":[126],"controller":[127],"(PRC)":[128],"maximizes":[131],"accuracy":[133],"during":[134,182],"pruning.":[135],"In":[136,156],"addition,":[137],"we":[138,160],"also":[139,233],"introduce":[140],"orthogonality":[141,180],"regularization":[142],"training":[144],"CNNs":[146],"to":[147,238],"redundancy":[149,173],"across":[150],"particular":[154],"layer.":[155],"proposed":[158,241],"approach,":[159],"prune":[161],"least":[163],"important":[164],"and,":[166],"at":[167,249],"same":[169],"time,":[170],"level":[174],"by":[178,267,278],"using":[179],"constraints":[181],"training.":[183],"Moreover,":[184],"unlike":[185],"most":[186],"previous":[187],"approaches,":[188],"our":[189],"approach":[190,259],"allows":[191],"directly":[192],"specifying":[193],"desired":[195],"error":[196],"tolerance":[197],"instead":[198],"level.":[202],"perform":[204],"extensive":[205],"experiments":[206],"object":[208,216],"classification":[209],"(LeNet,":[210],"VGG,":[211],"MobileNet,":[212],"ResNet)":[214],"detection":[217],"(SSD,":[218],"Faster-RCNN)":[220],"over":[221],"benchmarked":[222],"datasets":[223],"such":[224],"MNIST,":[226],"CIFAR,":[227],"GTSDB,":[228],"ImageNet,":[229],"MS-COCO.":[231],"several":[235],"ablation":[236],"studies":[237],"validate":[239],"approach.":[242],"compressed":[244],"can":[246],"be":[247],"deployed":[248],"run-time,":[250],"without":[251],"requiring":[252],"any":[253],"special":[254],"libraries":[255],"or":[256],"hardware.":[257],"reduces":[260],"VGG-16":[266],"impressive":[269],"factor":[270],"17.5X,":[272],"FLOPS":[277],"6.43X,":[279],"no":[281],"loss":[282],"accuracy,":[284],"significantly":[285],"outperforming":[286],"other":[287],"state-of-the-art":[288],"methods.":[291]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}