{"id":"https://openalex.org/W4399304317","doi":"https://doi.org/10.1145/3650200.3656622","title":"Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers","display_name":"Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399304317","doi":"https://doi.org/10.1145/3650200.3656622"},"language":"en","primary_location":{"id":"doi:10.1145/3650200.3656622","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656622","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656622","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656622","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101633365","display_name":"Zhengang Li","orcid":"https://orcid.org/0000-0001-6644-4761"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengang Li","raw_affiliation_strings":["Northeastern University, USA"],"raw_orcid":"https://orcid.org/0000-0001-6644-4761","affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067662998","display_name":"Alec Lu","orcid":"https://orcid.org/0000-0002-3315-7368"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alec Lu","raw_affiliation_strings":["Simon Fraser University, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3315-7368","affiliations":[{"raw_affiliation_string":"Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088784101","display_name":"Yanyue Xie","orcid":"https://orcid.org/0000-0002-4325-521X"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanyue Xie","raw_affiliation_strings":["Northeastern University, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4325-521X","affiliations":[{"raw_affiliation_string":"Northeastern University, United States of America","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078971265","display_name":"Zhenglun Kong","orcid":"https://orcid.org/0000-0002-8120-4456"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenglun Kong","raw_affiliation_strings":["Northeastern University, USA"],"raw_orcid":"https://orcid.org/0000-0002-8120-4456","affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083232044","display_name":"Mengshu Sun","orcid":"https://orcid.org/0000-0003-3540-1464"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengshu Sun","raw_affiliation_strings":["Beijing University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-3540-1464","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["ETH Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-2077-1246","affiliations":[{"raw_affiliation_string":"ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061359598","display_name":"Zhong Jia Xue","orcid":"https://orcid.org/0009-0000-7237-0236"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhong Jia Xue","raw_affiliation_strings":["Simon Fraser University, Canada"],"raw_orcid":"https://orcid.org/0009-0000-7237-0236","affiliations":[{"raw_affiliation_string":"Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089349472","display_name":"Peiyan Dong","orcid":"https://orcid.org/0000-0001-5287-5149"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peiyan Dong","raw_affiliation_strings":["Northeastern University, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-5287-5149","affiliations":[{"raw_affiliation_string":"Northeastern University, United States of America","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-0891-1231","affiliations":[{"raw_affiliation_string":"University of Connecticut, United States of America","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhi Wang","raw_affiliation_strings":["Northeastern University, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3024-7990","affiliations":[{"raw_affiliation_string":"Northeastern University, United States of America","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043582832","display_name":"Xue Lin","orcid":"https://orcid.org/0000-0001-6210-8883"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xue Lin","raw_affiliation_strings":["Northeastern University, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6210-8883","affiliations":[{"raw_affiliation_string":"Northeastern University, United States of America","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065889904","display_name":"Zhenman Fang","orcid":"https://orcid.org/0000-0003-0603-9697"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhenman Fang","raw_affiliation_strings":["Simon Fraser University, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0603-9697","affiliations":[{"raw_affiliation_string":"Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5101633365"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":1.6023,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83215882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"324","last_page":"337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9997000098228455,"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":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9965999722480774,"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":0.7727199792861938},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6480882167816162},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6383790373802185},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5924727320671082},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5502533912658691},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5111060738563538},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4964960217475891},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.47718489170074463},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.40717434883117676},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3784467577934265},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3776392936706543},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3205828070640564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31631505489349365},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3153679370880127},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29271987080574036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727199792861938},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6480882167816162},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6383790373802185},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5924727320671082},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5502533912658691},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5111060738563538},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4964960217475891},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.47718489170074463},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40717434883117676},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3784467577934265},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3776392936706543},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3205828070640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31631505489349365},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3153679370880127},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29271987080574036},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650200.3656622","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656622","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656622","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650200.3656622","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656622","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656622","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4891523138","display_name":null,"funder_award_id":"IIS-2310254, CCF-1937500, CNS-1909172","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399304317.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2194775991","https://openalex.org/W2300242332","https://openalex.org/W2549139847","https://openalex.org/W2593390416","https://openalex.org/W2739789140","https://openalex.org/W2773706593","https://openalex.org/W2796265726","https://openalex.org/W2963821229","https://openalex.org/W2963918968","https://openalex.org/W2964081807","https://openalex.org/W2965658867","https://openalex.org/W2967733054","https://openalex.org/W2982041622","https://openalex.org/W2982479999","https://openalex.org/W2982644126","https://openalex.org/W2998183051","https://openalex.org/W3034429256","https://openalex.org/W3035189477","https://openalex.org/W3035332806","https://openalex.org/W3096533519","https://openalex.org/W3098576111","https://openalex.org/W3109946440","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3139445856","https://openalex.org/W3158020960","https://openalex.org/W3168622113","https://openalex.org/W3173374050","https://openalex.org/W3174402370","https://openalex.org/W3177265267","https://openalex.org/W3184682079","https://openalex.org/W3195571952","https://openalex.org/W3204801262","https://openalex.org/W4211085526","https://openalex.org/W4214634256","https://openalex.org/W4221106024","https://openalex.org/W4285601701","https://openalex.org/W4321637298","https://openalex.org/W6734864916"],"related_works":["https://openalex.org/W4221139464","https://openalex.org/W4289827464","https://openalex.org/W2928062709","https://openalex.org/W3204400881","https://openalex.org/W3214410901","https://openalex.org/W3204296682","https://openalex.org/W3183118997","https://openalex.org/W2917767146","https://openalex.org/W2929170389","https://openalex.org/W4300097863"],"abstract_inverted_index":{"Vision":[0],"transformers":[1],"(ViTs)":[2],"have":[3],"demonstrated":[4],"their":[5],"superior":[6],"accuracy":[7],"for":[8,24,41,48,160],"computer":[9],"vision":[10],"tasks":[11],"compared":[12],"to":[13,43,90,116],"convolutional":[14],"neural":[15],"networks":[16],"(CNNs).":[17],"However,":[18],"ViT":[19,46],"models":[20,47,137],"are":[21],"often":[22],"computation-intensive":[23],"efficient":[25,45,79],"deployment":[26],"on":[27,112,147],"resource-limited":[28],"edge":[29],"devices.":[30],"This":[31],"work":[32],"proposes":[33],"Quasar-ViT,":[34],"a":[35,58,92,107],"hardware-oriented":[36,80],"quantization-aware":[37],"architecture":[38,119],"search":[39,81,120],"framework":[40],"ViTs,":[42],"design":[44],"hardware":[49,85],"implementation":[50],"while":[51],"preserving":[52],"the":[53,113,118,123,126,131,148,161],"accuracy.":[54],"First,":[55],"Quasar-ViT":[56],"trains":[57],"supernet":[59,71,98],"using":[60],"our":[61],"row-wise":[62],"flexible":[63],"mixed-precision":[64,67],"quantization":[65],"scheme,":[66],"weight":[68],"entanglement,":[69],"and":[70,87,121,130,141,155],"layer":[72],"scaling":[73],"techniques.":[74],"Then,":[75],"it":[76],"applies":[77],"an":[78],"algorithm,":[82],"integrated":[83],"with":[84,152],"latency":[86,102],"resource":[88],"modeling,":[89],"determine":[91],"series":[93,108],"of":[94,109],"optimal":[95],"subnets":[96],"from":[97],"under":[99],"different":[100],"inference":[101,133,145],"targets.":[103],"Finally,":[104],"we":[105],"propose":[106],"model-adaptive":[110],"designs":[111],"FPGA":[114,151],"platform":[115],"support":[117],"mitigate":[122],"gap":[124],"between":[125],"theoretical":[127],"computation":[128],"reduction":[129],"practical":[132],"speedup.":[134],"Our":[135],"searched":[136],"achieve":[138],"101.5,":[139],"159.6,":[140],"251.6":[142],"frames-per-second":[143],"(FPS)":[144],"speed":[146],"AMD/Xilinx":[149],"ZCU102":[150],"80.4%,":[153],"78.6%,":[154],"74.9%":[156],"top-1":[157],"accuracy,":[158],"respectively,":[159],"ImageNet":[162],"dataset,":[163],"consistently":[164],"outperforming":[165],"prior":[166],"works.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}