{"id":"https://openalex.org/W3126994728","doi":"https://doi.org/10.1109/tc.2021.3056929","title":"Enabling Highly Efficient Capsule Networks Processing Through Software-Hardware Co-Design","display_name":"Enabling Highly Efficient Capsule Networks Processing Through Software-Hardware Co-Design","publication_year":2021,"publication_date":"2021-02-03","ids":{"openalex":"https://openalex.org/W3126994728","doi":"https://doi.org/10.1109/tc.2021.3056929","mag":"3126994728"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2021.3056929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3056929","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Transactions on Computers","raw_type":"journal-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/A5010481801","display_name":"Xingyao Zhang","orcid":"https://orcid.org/0000-0002-8874-9520"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyao Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016298390","display_name":"Xin Fu","orcid":"https://orcid.org/0000-0002-9458-4769"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Fu","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051047559","display_name":"Donglin Zhuang","orcid":"https://orcid.org/0000-0003-3355-407X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Donglin Zhuang","raw_affiliation_strings":["Future System Architecture (FSA) Lab, University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future System Architecture (FSA) Lab, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024508481","display_name":"Chenhao Xie","orcid":"https://orcid.org/0000-0002-1399-0352"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenhao Xie","raw_affiliation_strings":["Pacific Northwest National Lab (PNNL), Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab (PNNL), Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Future System Architecture (FSA) Lab, University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future System Architecture (FSA) Lab, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.848,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7416859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"70","issue":"4","first_page":"495","last_page":"510"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.833439826965332},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5834928750991821},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5636303424835205},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5291070342063904},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5275484919548035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49310967326164246},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4483805298805237},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42199769616127014},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37923291325569153},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35890015959739685},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.33523011207580566},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.26884132623672485},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12614694237709045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833439826965332},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5834928750991821},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5636303424835205},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5291070342063904},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5275484919548035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49310967326164246},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4483805298805237},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42199769616127014},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37923291325569153},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35890015959739685},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33523011207580566},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26884132623672485},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12614694237709045}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2021.3056929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3056929","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G480180997","display_name":null,"funder_award_id":"DEAC05-76RL01830","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4898900696","display_name":null,"funder_award_id":"CCF-1619243","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7331131874","display_name":null,"funder_award_id":"CCF-1537085","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8333557126","display_name":null,"funder_award_id":"CCF-1900904","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8871425683","display_name":"Adaptive Key-value Store for Future Extreme Heterogeneous Systems","funder_award_id":"DP210101984","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W1667652561","https://openalex.org/W1975237352","https://openalex.org/W1981220134","https://openalex.org/W2084336274","https://openalex.org/W2107583051","https://openalex.org/W2112796928","https://openalex.org/W2128414660","https://openalex.org/W2128444504","https://openalex.org/W2204310803","https://openalex.org/W2335728318","https://openalex.org/W2508602506","https://openalex.org/W2518281301","https://openalex.org/W2518511512","https://openalex.org/W2590796488","https://openalex.org/W2605347906","https://openalex.org/W2612735730","https://openalex.org/W2785994986","https://openalex.org/W2790310590","https://openalex.org/W2799350897","https://openalex.org/W2802189604","https://openalex.org/W2809361304","https://openalex.org/W2895077924","https://openalex.org/W2899771611","https://openalex.org/W2901135043","https://openalex.org/W2901722832","https://openalex.org/W2904295992","https://openalex.org/W2904902077","https://openalex.org/W2905209374","https://openalex.org/W2907019248","https://openalex.org/W2913763165","https://openalex.org/W2933109814","https://openalex.org/W2963703618","https://openalex.org/W2963762721","https://openalex.org/W3016917092","https://openalex.org/W3101197104","https://openalex.org/W3118608800","https://openalex.org/W3149681544","https://openalex.org/W4246587277","https://openalex.org/W4297805688","https://openalex.org/W4302296459","https://openalex.org/W6637151318","https://openalex.org/W6703116779","https://openalex.org/W6733793881","https://openalex.org/W6743446608","https://openalex.org/W6748053814","https://openalex.org/W6750715008","https://openalex.org/W6751339499","https://openalex.org/W6756040250","https://openalex.org/W6756880974","https://openalex.org/W6758137187","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4375867731","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W2154356865","https://openalex.org/W1841000604"],"abstract_inverted_index":{"As":[0],"the":[1,4,8,15,25,37,56,62,66,73,76,80,93,99,105,131,138,160,167,174,179,182,192,198,204,230],"demand":[2],"for":[3,24,65,197,209,251],"image":[5,9,67],"processing":[6,27],"increases,":[7],"features":[10],"become":[11],"increasingly":[12],"complicated.":[13],"Although":[14],"Convolutional":[16],"Neural":[17],"Network":[18],"(CNN)":[19],"have":[20],"been":[21,31,85],"widely":[22],"adopted":[23],"imaging":[26],"tasks,":[28],"it":[29,83],"has":[30,84],"found":[32],"easily":[33],"misled":[34],"due":[35],"to":[36,54,190],"massive":[38,111],"usage":[39],"of":[40,79,102,173,185,213],"pooling":[41],"operations.":[42],"A":[43],"novel":[44],"neural":[45],"network":[46],"structure":[47],"called":[48],"Capsule":[49],"Networks":[50],"(CapsNet)":[51],"is":[52],"proposed":[53],"address":[55,126],"CNN":[57,211],"challenge":[58],"and":[59,69,108,115,145,162,170,246],"essentially":[60],"enhance":[61],"learning":[63],"ability":[64],"segmentation":[68],"object":[70],"detection.":[71],"Since":[72],"CapsNet":[74,103,120,231,252],"contains":[75],"high":[77],"volume":[78],"matrix":[81],"execution,":[82],"generally":[86],"accelerated":[87],"on":[88,122,241],"modern":[89,123],"GPU":[90],"platforms":[91],"with":[92,203,254],"highly":[94],"optimized":[95],"deep-learning":[96],"library.":[97],"However,":[98],"routing":[100,175,199],"procedure":[101],"introduces":[104],"special":[106],"program":[107],"execution":[109,121,232],"features,including":[110],"unshareable":[112],"intermediate":[113],"variables":[114],"intensive":[116],"synchronizations,":[117],"causing":[118],"inefficient":[119],"GPU.":[124],"To":[125],"these":[127],"challenges,":[128],"we":[129],"propose":[130],"software-hardware":[132],"co-designed":[133],"optimizations,":[134],"SH-CapsNet,":[135],"which":[136],"includes":[137],"software-level":[139],"optimizations":[140,226],"named":[141,151],"<i":[142,152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[143,153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S-CapsNet</i>":[144],"a":[146],"hybrid":[147],"computing":[148,207],"architecture":[149],"design":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">PIM-CapsNet</i>":[154],".":[155],"In":[156,177],"software-level,":[157],"S-CapsNet":[158],"reduces":[159],"computation":[161],"memory":[163,189],"accesses":[164],"by":[165],"exploiting":[166],"computational":[168],"redundancy":[169],"data":[171],"similarity":[172],"procedure.":[176],"hardware-level,":[178],"PIM-CapsNet":[180],"leverages":[181],"processing-in-memory":[183],"capability":[184,208],"today's":[186],"3D":[187],"stacked":[188],"conduct":[191],"off-chip":[193],"in-memory":[194],"acceleration":[195],"solution":[196],"procedure,":[200],"while":[201],"pipelining":[202],"GPU's":[205],"on-chip":[206],"accelerating":[210],"types":[212],"layers":[214],"in":[215],"CapsNet.":[216],"Evaluation":[217],"results":[218],"demonstrate":[219],"that":[220],"either":[221],"our":[222,235],"software":[223],"or":[224],"hardware":[225],"can":[227,237],"significantly":[228],"improve":[229],"efficiency.":[233],"Together,":[234],"co-design":[236],"achieve":[238],"greatly":[239],"improvement":[240],"both":[242],"performance":[243],"(3.41":[244],"x)":[245],"energy":[247],"savings":[248],"(68.72":[249],"percent)":[250],"inference,":[253],"negligible":[255],"accuracy":[256],"loss.":[257]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}