{"id":"https://openalex.org/W3159072220","doi":"https://doi.org/10.1109/iscas51556.2021.9401657","title":"Adaptive Quantization Method for CNN with Computational-Complexity-Aware Regularization","display_name":"Adaptive Quantization Method for CNN with Computational-Complexity-Aware Regularization","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3159072220","doi":"https://doi.org/10.1109/iscas51556.2021.9401657","mag":"3159072220"},"language":"en","primary_location":{"id":"doi:10.1109/iscas51556.2021.9401657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5110431996","display_name":"Kengo Nakata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kengo Nakata","raw_affiliation_strings":["Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024598865","display_name":"Daisuke Miyashita","orcid":"https://orcid.org/0000-0003-2108-3397"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daisuke Miyashita","raw_affiliation_strings":["Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007360587","display_name":"Jun Deguchi","orcid":"https://orcid.org/0000-0002-3414-5537"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Deguchi","raw_affiliation_strings":["Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025374739","display_name":"Ryuichi Fujimoto","orcid":"https://orcid.org/0000-0002-2374-7073"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryuichi Fujimoto","raw_affiliation_strings":["Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kioxia Corporation, Institute of Memory Technology Research & Development, Kawasaki, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2412,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87007346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9972000122070312,"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/T10320","display_name":"Neural Networks and Applications","score":0.9954000115394592,"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":0.6970557570457458},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6948965787887573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6935021877288818},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.635646402835846},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5910657644271851},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5248422622680664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5224836468696594},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.48883765935897827},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.45507872104644775},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.419141948223114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3705044984817505}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6970557570457458},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6948965787887573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6935021877288818},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.635646402835846},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5910657644271851},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5248422622680664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5224836468696594},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.48883765935897827},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.45507872104644775},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.419141948223114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3705044984817505},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"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:10.1109/iscas51556.2021.9401657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2108598243","https://openalex.org/W2118858186","https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2302255633","https://openalex.org/W2606722458","https://openalex.org/W2895531329","https://openalex.org/W2899771611","https://openalex.org/W2907793133","https://openalex.org/W2916954108","https://openalex.org/W2947527335","https://openalex.org/W2955052486","https://openalex.org/W2962914733","https://openalex.org/W2963163009","https://openalex.org/W2964861433","https://openalex.org/W2982041622","https://openalex.org/W2982479999","https://openalex.org/W3001133453","https://openalex.org/W3004392938","https://openalex.org/W3017746288","https://openalex.org/W3025897272","https://openalex.org/W3034940165","https://openalex.org/W4288026258","https://openalex.org/W4288413318","https://openalex.org/W6637373629","https://openalex.org/W6677919164","https://openalex.org/W6690026940","https://openalex.org/W6698183232","https://openalex.org/W6756040250","https://openalex.org/W6760069825","https://openalex.org/W6766057927","https://openalex.org/W6767597771","https://openalex.org/W6770425567","https://openalex.org/W6771595542","https://openalex.org/W6772080394","https://openalex.org/W6776320331"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"Quantization":[0],"is":[1,27,49,100,109,133],"a":[2,110,121,125,158],"typical":[3],"approach":[4],"toward":[5],"reducing":[6,19],"processing":[7],"time":[8,93,105,138,182],"for":[9,70,91,112],"inference":[10,20,92,114,137,181],"of":[11,39,76,98,139],"convolutional":[12],"neural":[13],"networks":[14],"(CNNs).":[15],"The":[16,61,143],"key":[17],"to":[18,33,44,50,184],"times":[21],"without":[22],"drastic":[23],"decreases":[24],"in":[25],"accuracy":[26,156,169],"allocating":[28],"optimal":[29,46,90,149],"bit":[30,47,80,150],"widths":[31],"according":[32],"each":[34],"layer":[35],"or":[36,73],"filter.":[37],"One":[38],"the":[40,68,79,84,95,104,113,136,163,171,175,185],"most":[41],"promising":[42],"ways":[43],"find":[45],"allocations":[48,81],"learn":[51],"quantization":[52],"step":[53],"size":[54,72],"and":[55,103],"weight":[56],"parameters":[57,66],"through":[58],"gradient":[59],"descent.":[60],"conventional":[62,85,164,186],"method":[63,86,123,145,177],"optimizes":[64],"those":[65],"under":[67,157],"constraint":[69],"model":[71],"memory":[74],"footprint":[75],"CNN.":[77],"However,":[78],"obtained":[82],"by":[83],"are":[87],"not":[88],"always":[89],"because":[94],"arithmetic":[96],"intensity":[97],"CNN":[99,141],"significantly":[101],"high,":[102],"spent":[106],"on":[107,170],"computing":[108],"bottleneck":[111],"time.":[115],"In":[116],"this":[117],"paper,":[118],"we":[119,129],"propose":[120],"regularization":[122],"using":[124],"computational-complexity":[126,160],"metric":[127],"(which":[128],"call":[130],"MACxbit)":[131],"that":[132,152],"correlated":[134],"with":[135],"quantized":[140],"models.":[142],"proposed":[144,176],"can":[146],"obtain":[147],"an":[148],"allocation":[151],"achieves":[153,178],"better":[154],"recognition":[155,168],"specified":[159],"target":[161],"than":[162],"method.":[165,187],"For":[166],"similar":[167],"optimized":[172],"ResNet-18":[173],"model,":[174],"21.0%":[179],"less":[180],"compared":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}