{"id":"https://openalex.org/W4392904583","doi":"https://doi.org/10.1109/icassp48485.2024.10448097","title":"Mixed Precision Neural Quantization with Multi-Objective Bayesian Optimization for on-Device Deployment","display_name":"Mixed Precision Neural Quantization with Multi-Objective Bayesian Optimization for on-Device Deployment","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904583","doi":"https://doi.org/10.1109/icassp48485.2024.10448097"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5057645083","display_name":"Srinivas Soumitri Miriyala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Srinivas S Miriyala","raw_affiliation_strings":["Samsung Research Institute,Bangalore","Samsung Research Institute, Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"Samsung Research Institute, Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042939692","display_name":"P K Suhas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P K Suhas","raw_affiliation_strings":["Samsung Research Institute,Bangalore","Samsung Research Institute, Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"Samsung Research Institute, Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533117","display_name":"Utsav P. Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Utsav Tiwari","raw_affiliation_strings":["Samsung Research Institute,Bangalore","Samsung Research Institute, Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"Samsung Research Institute, Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079783021","display_name":"Vikram N Rajendiran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vikram N Rajendiran","raw_affiliation_strings":["Samsung Research Institute,Bangalore","Samsung Research Institute, Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"Samsung Research Institute, Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057645083"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.7462,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69261019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6260","last_page":"6264"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval 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"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7295541763305664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955626606941223},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6180264949798584},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5000162124633789},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4941864311695099},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.45902782678604126},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.4442348778247833},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4223957359790802},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.404282808303833},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37481504678726196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32186639308929443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2670918107032776}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7295541763305664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955626606941223},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6180264949798584},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5000162124633789},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4941864311695099},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.45902782678604126},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.4442348778247833},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4223957359790802},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.404282808303833},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37481504678726196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32186639308929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2670918107032776},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"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/icassp48485.2024.10448097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":30,"referenced_works":["https://openalex.org/W2117502083","https://openalex.org/W2786771851","https://openalex.org/W2884150179","https://openalex.org/W2903260438","https://openalex.org/W2963122961","https://openalex.org/W2981751377","https://openalex.org/W2982041622","https://openalex.org/W2982479999","https://openalex.org/W3034940165","https://openalex.org/W3035677605","https://openalex.org/W3089812288","https://openalex.org/W3173470024","https://openalex.org/W3204960814","https://openalex.org/W4221155876","https://openalex.org/W4288026258","https://openalex.org/W4291963193","https://openalex.org/W4310147199","https://openalex.org/W4313045298","https://openalex.org/W4320721392","https://openalex.org/W4382466739","https://openalex.org/W4385848481","https://openalex.org/W4386075607","https://openalex.org/W6748224102","https://openalex.org/W6756979132","https://openalex.org/W6770425567","https://openalex.org/W6780116775","https://openalex.org/W6810049602","https://openalex.org/W6842065451","https://openalex.org/W6849678873","https://openalex.org/W6855812879"],"related_works":["https://openalex.org/W4318703531","https://openalex.org/W4304194161","https://openalex.org/W4386159657","https://openalex.org/W4252419006","https://openalex.org/W4226220869","https://openalex.org/W2809500545","https://openalex.org/W4291270681","https://openalex.org/W3176282186","https://openalex.org/W4387489555","https://openalex.org/W2973622361"],"abstract_inverted_index":{"Mixed-precision":[0],"quantization":[1],"has":[2],"emerged":[3],"as":[4],"a":[5,38,93,132],"solution":[6],"in":[7,92,102,135],"recent":[8],"times":[9,107],"for":[10,80,123],"accurate":[11],"inference":[12,89],"of":[13,47],"Deep":[14],"Neural":[15],"Networks":[16],"on":[17,27,58,129],"edge.":[18],"However":[19],"the":[20,51,56,59,67,83,87],"prior-art":[21],"is":[22,40,74],"far":[23],"from":[24],"being":[25],"deployable":[26],"embedded":[28,60],"devices":[29],"due":[30],"to":[31],"various":[32],"practical":[33],"limitations.":[34],"In":[35],"this":[36],"work,":[37],"pipeline":[39,73],"designed":[41],"that":[42],"a)":[43],"performs":[44],"layer-wise":[45],"assignment":[46],"bit-precisions,":[48],"b)":[49],"builds":[50],"quantized":[52],"graph,":[53],"c)":[54],"deploys":[55],"graph":[57],"device":[61],"(Galaxy":[62],"S23),":[63],"and":[64,69,85,105,112,116,119,126],"d)":[65],"measures":[66],"accuracy":[68,84,121],"on-device":[70,88],"performance.":[71],"This":[72],"optimized":[75],"using":[76],"multi-objective":[77],"Bayesian":[78],"Optimization":[79],"simultaneously":[81],"maximizing":[82],"minimizing":[86],"time,":[90],"resulting":[91],"Pareto":[94],"list.":[95],"The":[96],"best":[97],"configuration":[98],"among":[99],"them":[100],"resulted":[101],"3.16,":[103],"2.8,":[104],"2.57":[106],"model":[108],"compression,":[109],"31%,":[110],"26%":[111],"18%":[113],"latency":[114],"improvement":[115],"-0.01,":[117],"0.27,":[118],"0.08":[120],"drop":[122],"ResNet18,":[124],"MobileNetV2,":[125],"InceptionV3,":[127],"respectively,":[128],"ImageNet,":[130],"establishing":[131],"new":[133],"benchmark":[134],"mixed-precision":[136],"quantization.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}