{"id":"https://openalex.org/W4406220615","doi":"https://doi.org/10.1145/3711846","title":"Algorithm-Hardware Co-design for Accelerating Depthwise Separable CNNs","display_name":"Algorithm-Hardware Co-design for Accelerating Depthwise Separable CNNs","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406220615","doi":"https://doi.org/10.1145/3711846"},"language":"en","primary_location":{"id":"doi:10.1145/3711846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711846","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/382571315/3711846.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100368584","display_name":"Guoqing Li","orcid":"https://orcid.org/0000-0003-2075-8583"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Li","raw_affiliation_strings":["Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd, Jinan, China","Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd,  Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-2075-8583","affiliations":[{"raw_affiliation_string":"Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd, Jinan, China","institution_ids":["https://openalex.org/I4210144487"]},{"raw_affiliation_string":"Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd,  Jinan, China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064453711","display_name":"Rengang Li","orcid":"https://orcid.org/0000-0002-4297-4335"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rengang Li","raw_affiliation_strings":["Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd, Jinan, China","Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd,  Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd, Jinan, China","institution_ids":["https://openalex.org/I4210144487"]},{"raw_affiliation_string":"Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd,  Jinan, China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721491","display_name":"Tuo Li","orcid":"https://orcid.org/0000-0002-5813-9385"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuo Li","raw_affiliation_strings":["Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd, Jinan, China","Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd,  Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd, Jinan, China","institution_ids":["https://openalex.org/I4210144487"]},{"raw_affiliation_string":"Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co Ltd,  Jinan, China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022945347","display_name":"Tinghuan Chen","orcid":"https://orcid.org/0000-0002-9195-6619"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tinghuan Chen","raw_affiliation_strings":["The Chinese University of Hong Kong - Shenzhen, Shenzhen, China","The Chinese University of Hong Kong - Shenzhen,  Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong - Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"The Chinese University of Hong Kong - Shenzhen,  Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691593","display_name":"Meng Zhang","orcid":"https://orcid.org/0000-0003-1465-9714"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Zhang","raw_affiliation_strings":["Southeast University, Nanjing, China","Southeast University,  Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Southeast University,  Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081768631","display_name":"Henk Corporaal","orcid":"https://orcid.org/0000-0003-4506-5732"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Henk Corporaal","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, Netherlands","Eindhoven University of Technology,  Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology,  Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86590199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"30","issue":"2","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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":0.9975000023841858,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9944000244140625,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.9287048578262329},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.5835515260696411},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.5162860751152039},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4122983515262604},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38918012380599976},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.3190041184425354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9287048578262329},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.5835515260696411},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5162860751152039},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4122983515262604},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38918012380599976},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3190041184425354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3711846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711846","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:openaire/f258583d-92a3-4ed8-9578-468de74e9fd5","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/f258583d-92a3-4ed8-9578-468de74e9fd5","pdf_url":"https://pure.tue.nl/ws/files/382571315/3711846.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Li, G, Li, R, Li, T, Chen, T, Zhang, M & Corporaal, H 2025, 'Algorithm-Hardware Co-design for Accelerating Depthwise Separable CNNs', ACM Transactions on Design Automation of Electronic Systems, vol. 30, no. 2, 27. https://doi.org/10.1145/3711846","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire/f258583d-92a3-4ed8-9578-468de74e9fd5","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/f258583d-92a3-4ed8-9578-468de74e9fd5","pdf_url":"https://pure.tue.nl/ws/files/382571315/3711846.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Li, G, Li, R, Li, T, Chen, T, Zhang, M & Corporaal, H 2025, 'Algorithm-Hardware Co-design for Accelerating Depthwise Separable CNNs', ACM Transactions on Design Automation of Electronic Systems, vol. 30, no. 2, 27. https://doi.org/10.1145/3711846","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1087608875","display_name":null,"funder_award_id":"ZR2023QF056 and ZR2023QF050","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G1270356719","display_name":null,"funder_award_id":"ZR2023QF050","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G4350764097","display_name":null,"funder_award_id":"2023YFB4402900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6323708532","display_name":null,"funder_award_id":"ZR2023QF056","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G6575425435","display_name":null,"funder_award_id":"2024M751267","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7541412209","display_name":null,"funder_award_id":"62304197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406220615.pdf","grobid_xml":"https://content.openalex.org/works/W4406220615.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2194775991","https://openalex.org/W2276486856","https://openalex.org/W2302255633","https://openalex.org/W2549139847","https://openalex.org/W2585774018","https://openalex.org/W2604998962","https://openalex.org/W2616247523","https://openalex.org/W2797514659","https://openalex.org/W2808168148","https://openalex.org/W2809121165","https://openalex.org/W2883111419","https://openalex.org/W2883780447","https://openalex.org/W2901950140","https://openalex.org/W2913221350","https://openalex.org/W2924515500","https://openalex.org/W2928560789","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2976540144","https://openalex.org/W2982083293","https://openalex.org/W3000160544","https://openalex.org/W3008408165","https://openalex.org/W3010819965","https://openalex.org/W3034513523","https://openalex.org/W3035414587","https://openalex.org/W3072011699","https://openalex.org/W3095523882","https://openalex.org/W3100837220","https://openalex.org/W3102564565","https://openalex.org/W3113272803","https://openalex.org/W3126707779","https://openalex.org/W3166103364","https://openalex.org/W3168997536","https://openalex.org/W3171251238","https://openalex.org/W3173852813","https://openalex.org/W3214591391","https://openalex.org/W4200122786","https://openalex.org/W4200536695","https://openalex.org/W4207057190","https://openalex.org/W4213183277","https://openalex.org/W4214493665","https://openalex.org/W4214604703","https://openalex.org/W4214841728","https://openalex.org/W4214951654","https://openalex.org/W4221000689","https://openalex.org/W4226154274","https://openalex.org/W4248980851","https://openalex.org/W4282913477","https://openalex.org/W4282929256","https://openalex.org/W4285146087","https://openalex.org/W4289315680","https://openalex.org/W4308731133","https://openalex.org/W4323644242","https://openalex.org/W4392885482","https://openalex.org/W4393387539","https://openalex.org/W4401009767"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2009525028","https://openalex.org/W2096844293","https://openalex.org/W2363944576","https://openalex.org/W2351041855","https://openalex.org/W2570254841","https://openalex.org/W2518118925","https://openalex.org/W3159273459","https://openalex.org/W3152699334","https://openalex.org/W2390254310"],"abstract_inverted_index":{"Depthwise":[0],"separable":[1],"convolution":[2,16,28,48,132],"(DSC)":[3],"is":[4,99,110,135,155],"a":[5,19,64,180],"popular":[6],"method":[7,109],"for":[8,63,101,124],"constructing":[9],"lightweight":[10],"neural":[11],"networks.":[12],"However,":[13],"the":[14,26,31,58,71,75,80,85,89,93,96,105,118,139,177],"pointwise":[15],"(PWC)":[17],"has":[18],"much":[20],"larger":[21],"number":[22,81],"of":[23,35,82,143,179,183],"parameters":[24],"than":[25],"depthwise":[27],"(DWC),":[29],"causing":[30],"imbalanced":[32],"parameter":[33,66],"ratio":[34],"PWC":[36,60],"to":[37,56,78,112,137,157],"DWC.":[38],"In":[39],"this":[40],"article,":[41],"we":[42],"propose":[43],"an":[44],"efficient":[45],"and":[46,84,104,129,145,151],"hardware-efficiency":[47],"(Shared":[49],"Kernel":[50],"sliding":[51],"on":[52],"channel":[53,76,90],"Convolution,":[54],"SKC)":[55],"replace":[57],"redundant":[59],"in":[61,74,88],"DSC":[62,141],"balanced":[65],"ratio,":[67],"where":[68],"SKC":[69,98,146,160],"customizes":[70],"sharing":[72],"kernel":[73,107],"dimension":[77,91],"reduce":[79],"parameters,":[83],"local":[86],"connection":[87],"reduces":[92],"computation.":[94],"Furthermore,":[95],"proposed":[97,136,140],"suitable":[100],"Winograd":[102,131],"acceleration,":[103],"large":[106],"decomposition":[108],"introduced":[111],"facilitate":[113],"its":[114],"use.":[115],"We":[116],"implement":[117],"first":[119],"Winograd-based":[120],"FPGA":[121],"hardware":[122],"accelerator":[123,169],"DSCNets.":[125],"The":[126],"shared":[127],"1D":[128],"2D":[130],"computing":[133],"engine":[134],"compute":[138],"consisting":[142],"DWC":[144],"efficiently.":[147],"An":[148],"alternating":[149],"loading":[150],"reusing":[152],"storage":[153],"approach":[154],"developed":[156],"efficiently":[158],"load":[159],"input":[161],"feature":[162],"maps.":[163],"Experimental":[164],"results":[165],"show":[166],"our":[167],"DSC-based":[168],"can":[170],"achieve":[171],"20\u00d7":[172],"higher":[173],"power":[174],"efficiency":[175],"at":[176],"cost":[178],"small":[181],"loss":[182],"accuracy":[184],"by":[185],"algorithm-hardware":[186],"co-design":[187],"compared":[188],"with":[189],"traditional":[190],"accelerators.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}