{"id":"https://openalex.org/W4414197870","doi":"https://doi.org/10.1109/dac63849.2025.11132777","title":"Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming","display_name":"Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197870","doi":"https://doi.org/10.1109/dac63849.2025.11132777"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11132777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"article","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/A5052384550","display_name":"Zihao Deng","orcid":"https://orcid.org/0000-0002-7247-4040"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zihao Deng","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061847219","display_name":"Sayeh Sharify","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158408","display_name":"Matrix Research (United States)","ror":"https://ror.org/04mw0p229","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158408"]},{"id":"https://openalex.org/I4210106084","display_name":"Matrix Engineering (United States)","ror":"https://ror.org/01ktbtm29","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106084"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayeh Sharify","raw_affiliation_strings":["d-Matrix Corp"],"affiliations":[{"raw_affiliation_string":"d-Matrix Corp","institution_ids":["https://openalex.org/I4210158408","https://openalex.org/I4210106084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770129","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-9075-2833"},"institutions":[{"id":"https://openalex.org/I4210158408","display_name":"Matrix Research (United States)","ror":"https://ror.org/04mw0p229","country_code":"US","type":"company","lineage":["https://openalex.org/I4210158408"]},{"id":"https://openalex.org/I4210106084","display_name":"Matrix Engineering (United States)","ror":"https://ror.org/01ktbtm29","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106084"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["d-Matrix Corp"],"affiliations":[{"raw_affiliation_string":"d-Matrix Corp","institution_ids":["https://openalex.org/I4210158408","https://openalex.org/I4210106084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090899796","display_name":"Michael Orshansky","orcid":"https://orcid.org/0000-0002-6223-4748"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Orshansky","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052384550"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25640946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9966999888420105,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9966999888420105,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9794999957084656,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9775999784469604,"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/quantization","display_name":"Quantization (signal processing)","score":0.859000027179718},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4733000099658966},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4325999915599823},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.42399999499320984},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.3361999988555908},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.3287999927997589}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.859000027179718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5623000264167786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4869000017642975},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4146000146865845},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.2741999924182892}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11132777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2979826702","https://openalex.org/W2982041622","https://openalex.org/W2982479999","https://openalex.org/W3034429256","https://openalex.org/W3034940165","https://openalex.org/W3094502228","https://openalex.org/W3096533519","https://openalex.org/W3204960814","https://openalex.org/W4249009392","https://openalex.org/W4280575426","https://openalex.org/W4312310654","https://openalex.org/W4382466739","https://openalex.org/W4390190118","https://openalex.org/W4390871868","https://openalex.org/W4393157004","https://openalex.org/W4401568520"],"related_works":[],"abstract_inverted_index":{"Quantization":[0],"is":[1],"a":[2,66,87,97],"widely":[3],"used":[4],"technique":[5],"to":[6,39,60],"compress":[7],"neural":[8],"networks.":[9],"Assigning":[10],"uniform":[11],"bit-widths":[12,38,92],"across":[13,54],"all":[14],"layers":[15,55],"can":[16],"result":[17],"in":[18],"significant":[19],"accuracy":[20],"degradation":[21],"at":[22,27],"low":[23],"precision":[24],"and":[25,114],"inefficiency":[26],"high":[28],"precision.":[29],"Mixed-precision":[30],"quantization":[31,52,76,104,126],"(MPQ)":[32],"addresses":[33],"this":[34],"by":[35,95],"assigning":[36],"varied":[37],"layers,":[40],"optimizing":[41,96],"the":[42],"accuracy-efficiency":[43],"trade-off.":[44],"Existing":[45],"sensitivity-based":[46,68],"methods":[47],"for":[48],"MPQ":[49,69,99],"assume":[50],"that":[51,71,121],"errors":[53,82,105],"are":[56,93],"independent,":[57],"which":[58],"leads":[59],"suboptimal":[61],"choices.":[62],"We":[63],"introduce":[64],"CLADO,":[65],"practical":[67],"algorithm":[70],"captures":[72],"cross-layer":[73,81,103],"dependency":[74],"of":[75],"error.":[77],"CLADO":[78,122],"approximates":[79],"pairwise":[80],"using":[83,106],"linear":[84],"equations":[85],"on":[86,102,118],"small":[88],"data":[89],"subset.":[90],"Layerwise":[91],"assigned":[94],"new":[98],"formulation":[100],"based":[101],"an":[107],"Integer":[108],"Quadratic":[109],"Program.":[110],"Experiments":[111],"with":[112],"CNN":[113],"vision":[115],"transformer":[116],"models":[117],"ImageNet":[119],"demonstrate":[120],"achieves":[123],"state-of-the-art":[124],"mixed-precision":[125],"performance.":[127],"Code":[128],"repository":[129],"available":[130],"here.<sup":[131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132,134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[133],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://github.com/JamesTuna/CLADOMPQ":[135]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
