{"id":"https://openalex.org/W4404133810","doi":"https://doi.org/10.1145/3649329.3656516","title":"QUQ: Quadruplet Uniform Quantization for Efficient Vision Transformer Inference","display_name":"QUQ: Quadruplet Uniform Quantization for Efficient Vision Transformer Inference","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404133810","doi":"https://doi.org/10.1145/3649329.3656516"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3656516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3656516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059647894","display_name":"Xinkuang Geng","orcid":"https://orcid.org/0000-0003-3673-237X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinkuang Geng","raw_affiliation_strings":["Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3673-237X","affiliations":[{"raw_affiliation_string":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005839811","display_name":"Siting Liu","orcid":"https://orcid.org/0000-0003-0505-8183"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siting Liu","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0505-8183","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358856","display_name":"Leibo Liu","orcid":"https://orcid.org/0000-0001-7548-4116"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leibo Liu","raw_affiliation_strings":["School of Integrated Circuits and The National Lab for Information Science and Technology, Tsinghua University, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7548-4116","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits and The National Lab for Information Science and Technology, Tsinghua University, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005550142","display_name":"Jie Han","orcid":"https://orcid.org/0000-0002-8849-4994"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jie Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8849-4994","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019717600","display_name":"Honglan Jiang","orcid":"https://orcid.org/0000-0003-3705-4240"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglan Jiang","raw_affiliation_strings":["Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3705-4240","affiliations":[{"raw_affiliation_string":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9991999864578247,"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":0.9991999864578247,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/computer-science","display_name":"Computer science","score":0.610981285572052},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5981547236442566},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5897932052612305},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5525029301643372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5281384587287903},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4562689960002899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33874183893203735},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13233682513237},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1321280300617218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.610981285572052},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5981547236442566},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5897932052612305},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5525029301643372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281384587287903},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4562689960002899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33874183893203735},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13233682513237},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1321280300617218},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3656516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3656516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6329299072","display_name":null,"funder_award_id":"2022YFB4500200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8355552838","display_name":null,"funder_award_id":"62374108","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2945652047","https://openalex.org/W3138516171","https://openalex.org/W4304080501","https://openalex.org/W4313069943","https://openalex.org/W4390873361"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W4321636575","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"While":[0],"exhibiting":[1],"superior":[2],"performance":[3],"in":[4,12,58],"many":[5],"tasks,":[6],"vision":[7],"transformers":[8],"(ViTs)":[9],"face":[10],"challenges":[11],"quantization.":[13],"Some":[14],"existing":[15],"low-bit-width":[16],"quantization":[17,49,85,117],"techniques":[18],"cannot":[19],"effectively":[20],"cover":[21],"the":[22,62,81,104,121],"whole":[23],"inference":[24],"process":[25],"of":[26,55,106],"ViTs,":[27],"leading":[28],"to":[29,51,102,130,142],"an":[30,87,107,150],"additional":[31],"memory":[32],"overhead":[33],"(22.3%-172.6%)":[34],"compared":[35],"with":[36,53,75,132,136,152],"corresponding":[37],"fully":[38,127],"quantized":[39,74],"models.":[40],"To":[41,79],"address":[42],"this":[43],"issue,":[44],"we":[45],"propose":[46],"quadruplet":[47],"uniform":[48,138],"(QUQ)":[50],"deal":[52],"data":[54,64],"various":[56],"distributions":[57],"ViT.":[59],"QUQ":[60,114,140],"divides":[61],"entire":[63],"range":[65],"into":[66],"at":[67],"most":[68],"four":[69],"subranges":[70],"that":[71,113,125],"are":[72,100],"uniformly":[73],"different":[76],"scale":[77],"factors.":[78],"determine":[80],"partition":[82],"scheme":[83,124],"and":[84,97,155],"parameters,":[86],"efficient":[88,108],"relaxation":[89],"algorithm":[90],"is":[91,120],"proposed":[92],"accordingly.":[93],"Moreover,":[94],"dedicated":[95],"encoding":[96],"decoding":[98],"strategies":[99],"devised":[101],"facilitate":[103],"design":[105],"accelerator.":[109],"Experimental":[110],"results":[111],"show":[112],"surpasses":[115],"state-of-the-art":[116],"techniques;":[118],"it":[119],"first":[122],"viable":[123],"can":[126],"quantize":[128],"ViTs":[129],"6-bit":[131],"acceptable":[133],"accuracy.":[134],"Compared":[135],"conventional":[137],"quantization,":[139],"leads":[141],"not":[143],"only":[144],"a":[145],"higher":[146],"accuracy":[147],"but":[148],"also":[149],"accelerator":[151],"lower":[153],"area":[154],"power.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}