{"id":"https://openalex.org/W3091445043","doi":"https://doi.org/10.1109/icip40778.2020.9191267","title":"Reinforcement Learning-Based Layer-Wise Quantization For Lightweight Deep Neural Networks","display_name":"Reinforcement Learning-Based Layer-Wise Quantization For Lightweight Deep Neural Networks","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3091445043","doi":"https://doi.org/10.1109/icip40778.2020.9191267","mag":"3091445043"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9191267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9191267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","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/A5110144149","display_name":"Juri Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juri Jung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599744","display_name":"Jonghee Kim","orcid":"https://orcid.org/0000-0003-4836-2038"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonghee Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086829943","display_name":"Youngeun Kim","orcid":"https://orcid.org/0000-0001-9905-9528"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngeun Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069759184","display_name":"Changick Kim","orcid":"https://orcid.org/0000-0001-9323-8488"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changick Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0854,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34352229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"3070","last_page":"3074"},"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":0.9994000196456909,"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":0.8874953389167786},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8157658576965332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7647818326950073},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.6381843686103821},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6275473833084106},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5305267572402954},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4389183521270752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4069954752922058}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8874953389167786},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8157658576965332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7647818326950073},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.6381843686103821},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6275473833084106},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5305267572402954},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4389183521270752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4069954752922058},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9191267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9191267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","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":35,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1757796397","https://openalex.org/W1902934009","https://openalex.org/W1996901117","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2300242332","https://openalex.org/W2405920868","https://openalex.org/W2412782625","https://openalex.org/W2469490737","https://openalex.org/W2524428287","https://openalex.org/W2810704618","https://openalex.org/W2921676720","https://openalex.org/W2962835968","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963114950","https://openalex.org/W2963363373","https://openalex.org/W2963989532","https://openalex.org/W2964014389","https://openalex.org/W3022782695","https://openalex.org/W3024127982","https://openalex.org/W3118608800","https://openalex.org/W4298857966","https://openalex.org/W6637373629","https://openalex.org/W6637967152","https://openalex.org/W6639703010","https://openalex.org/W6649495467","https://openalex.org/W6698200048","https://openalex.org/W6714058667","https://openalex.org/W6720242923","https://openalex.org/W6726275242","https://openalex.org/W6727208969","https://openalex.org/W6758508162","https://openalex.org/W6777312563"],"related_works":["https://openalex.org/W2599472179","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4319430125","https://openalex.org/W2906239812","https://openalex.org/W4289100296","https://openalex.org/W2962761403"],"abstract_inverted_index":{"Network":[0],"quantization":[1,65,103,147],"has":[2],"been":[3],"widely":[4],"studied":[5],"to":[6,155],"compress":[7],"the":[8,18,25,31,40,43,53,74,89,92,97,101,119,123,130,150,153,157,161],"deep":[9],"neural":[10],"network":[11,19],"in":[12,35,51,57],"mobile":[13],"devices.":[14],"Conventional":[15],"methods":[16],"quantize":[17],"parameters":[20,34,47,77],"of":[21,30,33,42,76,129],"all":[22],"layers":[23],"with":[24,45,126,133],"same":[26],"fixed":[27],"precision,":[28],"regardless":[29],"number":[32,75],"each":[36,79,106],"layer.":[37,107],"However,":[38],"quantizing":[39],"weights":[41],"layer":[44,80],"many":[46],"is":[48],"more":[49],"effective":[50],"reducing":[52],"model":[54,121],"size.":[55],"Accordingly,":[56],"this":[58,110],"paper,":[59],"we":[60,72,113],"propose":[61],"a":[62,82,95],"novel":[63],"mixed-precision":[64],"method":[66],"based":[67],"on":[68,122],"reinforcement":[69],"learning.":[70],"Specifically,":[71],"utilize":[73],"at":[78],"as":[81,94],"prior":[83],"for":[84,105,118,149],"our":[85,141],"framework.":[86],"By":[87,108],"using":[88],"accuracy":[90],"and":[91,152],"bit-width":[93],"reward,":[96],"proposed":[98],"framework":[99,142],"determines":[100],"optimal":[102,146],"policy":[104,111,148],"applying":[109],"sequentially,":[112],"achieve":[114],"weighted-average":[115],"2.97":[116],"bits":[117],"VGG-16":[120],"CIFAR-10":[124],"dataset":[125],"no":[127],"degradation":[128],"accuracy,":[131],"compared":[132],"its":[134],"full-precision":[135],"baseline.":[136],"We":[137],"also":[138],"show":[139],"that":[140],"can":[143],"provide":[144],"an":[145],"VGG-Net":[151],"ResNet":[154],"minimize":[156],"storage":[158],"while":[159],"preserving":[160],"accuracy.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}