{"id":"https://openalex.org/W3028526058","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207533","title":"FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks","display_name":"FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3028526058","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207533","mag":"3028526058"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.10142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alberto Marchisio","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alberto Marchisio","raw_affiliation_strings":["Technische Universit\u00e4t Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Beatrice Bussolino","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Beatrice Bussolino","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alessio Colucci","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alessio Colucci","raw_affiliation_strings":["Technische Universit\u00e4t Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Muhammad Abdullah Hanif","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Muhammad Abdullah Hanif","raw_affiliation_strings":["Technische Universit\u00e4t Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maurizio Martina","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maurizio Martina","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guido Masera","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Guido Masera","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":null,"display_name":"Muhammad Shafique","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Muhammad Shafique","raw_affiliation_strings":["Technische Universit\u00e4t Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.598,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74485258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":0.995199978351593,"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":0.995199978351593,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9922999739646912,"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"}},{"id":"https://openalex.org/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7524999976158142},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7347000241279602},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5745000243186951},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5741999745368958},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5156000256538391},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997999787330627},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7524999976158142},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7347000241279602},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5741999745368958},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4864000082015991},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.10142","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.10142","pdf_url":"https://arxiv.org/pdf/1905.10142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.10142","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.10142","pdf_url":"https://arxiv.org/pdf/1905.10142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2132968152","https://openalex.org/W2798919674","https://openalex.org/W2901135043","https://openalex.org/W2945789436","https://openalex.org/W2964054038","https://openalex.org/W2974437627","https://openalex.org/W2990982501","https://openalex.org/W2995059005","https://openalex.org/W3005346446","https://openalex.org/W6600115225","https://openalex.org/W6634326774","https://openalex.org/W6638524475","https://openalex.org/W6639794760","https://openalex.org/W6697452822","https://openalex.org/W6728479541","https://openalex.org/W6739622702","https://openalex.org/W6743446608","https://openalex.org/W6743688258","https://openalex.org/W6746407912","https://openalex.org/W6748053814","https://openalex.org/W6749845547","https://openalex.org/W6758353405","https://openalex.org/W6758907814","https://openalex.org/W6762883154","https://openalex.org/W6763958294","https://openalex.org/W6776455980"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Capsule":[1],"Networks":[2,14],"(CapsNets)":[3],"have":[4,256],"shown":[5],"improved":[6],"performance":[7],"compared":[8,228],"to":[9,72,149,169,229,246],"the":[10,23,34,44,48,54,58,73,94,98,110,171,201,205,213,218,225,230,237],"traditional":[11],"Convolutional":[12],"Neural":[13],"(CNNs),":[15],"by":[16,176,204,232,241],"encoding":[17],"and":[18,47,100,109,125,138,142,180,193,252],"preserving":[19,217],"spatial":[20,49],"relationships":[21],"between":[22,249],"detected":[24],"features":[25],"in":[26,57,93,145,212],"a":[27,116,126],"better":[28],"way.":[29],"This":[30],"is":[31,63,69,168],"achieved":[32,253],"through":[33,186],"so-called":[35],"Capsules":[36],"(i.e.,":[37],"groups":[38],"of":[39,53,61,77,97,174,188,200],"neurons)":[40],"that":[41,82,120,198],"encode":[42],"both":[43],"instantiation":[45],"probability":[46],"information.":[50],"However,":[51],"one":[52,199],"major":[55],"hurdles":[56],"wide":[59],"adoption":[60],"CapsNets":[62,175],"their":[64,78,106],"gigantic":[65],"training":[66,95,107,214,250],"time,":[67,215],"which":[68],"primarily":[70],"due":[71],"relatively":[74],"higher":[75],"complexity":[76],"new":[79],"constituting":[80],"elements":[81],"are":[83],"different":[84,91,189],"from":[85],"CNNs.In":[86],"this":[87],"paper,":[88],"we":[89,114],"implement":[90],"optimizations":[92,104,124],"loop":[96],"CapsNets,":[99],"investigate":[101],"how":[102],"these":[103],"affect":[105],"speed":[108],"accuracy.":[111,254],"Towards":[112],"this,":[113],"propose":[115,160],"novel":[117,127],"framework":[118,207,259],"FasTrCaps":[119,206,242],"integrates":[121],"multiple":[122],"lightweight":[123],"learning":[128,190],"rate":[129,191],"policy":[130],"called":[131],"WarmAdaBatch":[132],"(that":[133],"jointly":[134],"performs":[135],"warm":[136],"restarts":[137],"adaptive":[139],"batch":[140,194],"size),":[141],"steers":[143],"them":[144],"an":[146],"appropriate":[147],"way":[148],"provide":[150],"high":[151,184],"training-loop":[152],"speedup":[153],"at":[154],"minimal":[155],"accuracy":[156,185,219,222],"loss.":[157],"We":[158,196,255],"also":[159],"weight":[161],"sharing":[162],"for":[163,224],"capsule":[164],"layers.":[165],"The":[166],"goal":[167],"reduce":[170],"hardware":[172],"requirements":[173],"removing":[177],"unused/redundant":[178],"connections":[179],"capsules,":[181],"while":[182,216],"keeping":[183],"tests":[187],"policies":[192],"sizes.":[195],"demonstrate":[197],"solutions":[202,239],"generated":[203,240],"can":[208,243],"achieve":[209],"58.6%":[210],"reduction":[211],"(even":[220],"0.12%":[221],"improvement":[223],"MNIST":[226],"dataset),":[227],"CapsNet":[231],"Google":[233],"Brain":[234],"[25].":[235],"Moreover,":[236],"Pareto-optimal":[238],"be":[244],"leveraged":[245],"realize":[247],"trade-offs":[248],"time":[251],"open-sourced":[257],"our":[258],"on":[260],"GitHub1.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-05-29T00:00:00"}