{"id":"https://openalex.org/W4409641040","doi":"https://doi.org/10.1109/tmc.2025.3562721","title":"SPViT: Accelerate Vision Transformer Inference on Mobile Devices via Adaptive Splitting and Offloading","display_name":"SPViT: Accelerate Vision Transformer Inference on Mobile Devices via Adaptive Splitting and Offloading","publication_year":2025,"publication_date":"2025-04-21","ids":{"openalex":"https://openalex.org/W4409641040","doi":"https://doi.org/10.1109/tmc.2025.3562721"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2025.3562721","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3562721","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tmc.2025.3562721","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115603213","display_name":"Sifan Zhao","orcid":"https://orcid.org/0009-0000-7735-3187"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Zhao","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0000-7735-3187","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100543143","display_name":"Liu Tongtong","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtong Liu","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-1651-7784","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3934-7605","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018644308","display_name":"Dezhong Yao","orcid":"https://orcid.org/0000-0003-0336-0522"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhong Yao","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0336-0522","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0704,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7681647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"24","issue":"10","first_page":"9303","last_page":"9318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9714000225067139,"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"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9714000225067139,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.963100016117096,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.949999988079071,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"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":0.825764000415802},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5800558924674988},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5489429235458374},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.4560617506504059},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.38373175263404846},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3495323061943054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2311832308769226},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09060350060462952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.825764000415802},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5800558924674988},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5489429235458374},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.4560617506504059},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.38373175263404846},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3495323061943054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2311832308769226},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09060350060462952}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2025.3562721","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3562721","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tmc.2025.3562721","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3562721","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6100000143051147,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G6049162292","display_name":"\u9762\u5411\u8fb9\u7f18\u73af\u5883\u7684\u6df1\u5ea6\u5b66\u4e60\u7cfb\u7edf\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072204","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2789876780","https://openalex.org/W2950865323","https://openalex.org/W3121523901","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3159727696","https://openalex.org/W3168905915","https://openalex.org/W3172990466","https://openalex.org/W3205965083","https://openalex.org/W4214493665","https://openalex.org/W4214634256","https://openalex.org/W4293023328","https://openalex.org/W4312349930","https://openalex.org/W4312677967","https://openalex.org/W4312881242","https://openalex.org/W4313162985","https://openalex.org/W4315483911","https://openalex.org/W4321636820","https://openalex.org/W4365446402","https://openalex.org/W4366957282","https://openalex.org/W4378697133","https://openalex.org/W4381416086","https://openalex.org/W4385245566","https://openalex.org/W4386065441","https://openalex.org/W4386066311","https://openalex.org/W4386071870","https://openalex.org/W4386072014","https://openalex.org/W4386076193","https://openalex.org/W4386106400","https://openalex.org/W4386699354","https://openalex.org/W4388874804","https://openalex.org/W4389524599","https://openalex.org/W4394597936"],"related_works":["https://openalex.org/W3034529322","https://openalex.org/W2055243143","https://openalex.org/W2115913271","https://openalex.org/W2113597336","https://openalex.org/W2048100608","https://openalex.org/W2090296580","https://openalex.org/W1576249345","https://openalex.org/W4243905374","https://openalex.org/W2785815065","https://openalex.org/W1796074903"],"abstract_inverted_index":{"The":[0],"Vision":[1],"Transformer":[2],"(ViT),":[3],"which":[4],"benefits":[5],"from":[6],"utilizing":[7],"self-attention":[8],"mechanisms,":[9],"has":[10,32],"demonstrated":[11],"superior":[12],"accuracy":[13],"compared":[14],"to":[15,19,45,110,126,148],"CNNs.":[16],"However,":[17],"due":[18],"the":[20,95,106,128],"expensive":[21],"computational":[22,129],"costs,":[23],"deploying":[24,50],"and":[25,55,68,114,122,130],"inferring":[26],"ViTs":[27,51],"on":[28,52,75,105,133,137],"resource-constrained":[29],"mobile":[30,53,76],"devices":[31,54],"become":[33],"a":[34,90],"challenge.":[35],"To":[36],"resolve":[37],"this":[38,60],"challenge,":[39],"we":[40,62,100,119],"conducted":[41],"an":[42,65,102],"empirical":[43],"analysis":[44],"identify":[46],"performance":[47],"bottlenecks":[48],"in":[49],"explored":[56],"viable":[57],"solutions.":[58],"In":[59],"paper,":[61],"propose":[63,101],"SPViT,":[64],"adaptive":[66,115],"split":[67],"offloading":[69],"method":[70],"that":[71],"accelerates":[72],"ViT":[73,83],"inference":[74,81,144],"devices.":[77,87],"SPViT":[78,141],"executes":[79],"collaborative":[80],"of":[82],"across":[84,150],"available":[85],"edge":[86],"We":[88],"introduce":[89],"fine-grained":[91],"splitting":[92],"technique":[93],"for":[94],"vision":[96],"transformer":[97],"structure.":[98],"Furthermore,":[99],"algorithm":[103],"based":[104],"Auto":[107],"Regression":[108],"model":[109],"predict":[111],"partition":[112],"latency":[113,145],"offload":[116],"partitions.":[117],"Finally,":[118],"design":[120],"offline":[121],"online":[123],"optimization":[124],"methods":[125],"minimize":[127],"communication":[131],"overhead":[132],"each":[134],"device.":[135],"Based":[136],"real-world":[138],"prototype":[139],"experiments,":[140],"effectively":[142],"reduces":[143],"by":[146],"2.2x":[147],"3.3x":[149],"four":[151],"state-of-the-art":[152],"models.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}