{"id":"https://openalex.org/W4385079938","doi":"https://doi.org/10.1109/iscas46773.2023.10181695","title":"An Adaptive Quantization Method for CNN Activations","display_name":"An Adaptive Quantization Method for CNN Activations","publication_year":2023,"publication_date":"2023-05-21","ids":{"openalex":"https://openalex.org/W4385079938","doi":"https://doi.org/10.1109/iscas46773.2023.10181695"},"language":"en","primary_location":{"id":"doi:10.1109/iscas46773.2023.10181695","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas46773.2023.10181695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5104728939","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0002-8220-9726"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["School of Microelectronics, Tianjin University,Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Tianjin University,Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409523","display_name":"Qiang Liu","orcid":"https://orcid.org/0000-0003-1375-0508"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Liu","raw_affiliation_strings":["School of Microelectronics, Tianjin University,Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Tianjin University,Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8992272615432739},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7817079424858093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7289913892745972},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41158610582351685},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.4106053411960602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40481922030448914},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37733137607574463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17458117008209229}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8992272615432739},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7817079424858093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289913892745972},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41158610582351685},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.4106053411960602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40481922030448914},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37733137607574463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17458117008209229},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas46773.2023.10181695","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas46773.2023.10181695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8520571335","display_name":null,"funder_award_id":"U21B2031","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W2786771851","https://openalex.org/W2914552857","https://openalex.org/W2963122961","https://openalex.org/W2963163009","https://openalex.org/W2963480671","https://openalex.org/W2970601456","https://openalex.org/W3035006120","https://openalex.org/W3035205784","https://openalex.org/W3035826382","https://openalex.org/W3035855442","https://openalex.org/W3038470071","https://openalex.org/W3045214680","https://openalex.org/W3111779990","https://openalex.org/W3127311621","https://openalex.org/W3130476968","https://openalex.org/W3132747998","https://openalex.org/W3159627798","https://openalex.org/W3166117652","https://openalex.org/W3171513315","https://openalex.org/W3206196385","https://openalex.org/W4308096615","https://openalex.org/W6748224102","https://openalex.org/W6749781174","https://openalex.org/W6758830090","https://openalex.org/W6767298317","https://openalex.org/W6779175415","https://openalex.org/W6779813529","https://openalex.org/W6791264967","https://openalex.org/W6846764651"],"related_works":["https://openalex.org/W2386387936","https://openalex.org/W2211820962","https://openalex.org/W4281832382","https://openalex.org/W4225010712","https://openalex.org/W3196579076","https://openalex.org/W2367950322","https://openalex.org/W2392110728","https://openalex.org/W202916971","https://openalex.org/W3033395450","https://openalex.org/W4322616423"],"abstract_inverted_index":{"The":[0],"post-training":[1],"compression":[2],"based":[3],"on":[4,29,114],"affine":[5],"quantization":[6,22,41,66,78,86,94,130],"is":[7,46,104,132],"a":[8,106],"common":[9],"technology":[10],"to":[11,36,51,74],"improve":[12],"the":[13,38,52,55,77,85,93,98,101,111,135,144],"efficiency":[14],"of":[15,40,54,88,137],"embedded":[16],"neural":[17],"network":[18],"accelerators.":[19],"Current":[20],"state-of-the-art":[21],"schemes":[23],"for":[24,68],"CNN":[25],"activations":[26,69,89,99],"usually":[27],"rely":[28],"calibration":[30],"dataset":[31],"with":[32,134],"better":[33],"data":[34,58],"representation":[35],"reduce":[37],"possibility":[39],"overflow":[42,79,87,102,131],"in":[43,59,80,125,140],"inference,":[44],"which":[45],"not":[47],"always":[48],"effective":[49],"due":[50],"uncertainty":[53],"inference":[56,126,149],"input":[57],"practice.":[60],"This":[61,82],"paper":[62],"proposes":[63],"an":[64],"adaptive":[65],"method":[67,83,113],"and":[70,96,116,118,142,151],"its":[71],"hardware-friendly":[72],"design":[73],"directly":[75],"address":[76],"inference.":[81],"monitors":[84],"on-the-fly,":[90],"adaptively":[91],"updates":[92],"parameters,":[95],"re-quantizes":[97],"when":[100],"degree":[103],"over":[105],"tunable":[107],"threshold.":[108],"We":[109],"evaluate":[110],"proposed":[112],"VGG16":[115],"MobileNetV2":[117],"experiment":[119],"results":[120],"show":[121],"that":[122],"11%":[123],"improvement":[124],"accuracy":[127,150],"at":[128],"severe":[129],"achieved":[133],"cost":[136],"3%":[138],"increase":[139],"runtime,":[141],"tuning":[143],"threshold":[145],"enables":[146],"trade-off":[147],"between":[148],"speed.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}