{"id":"https://openalex.org/W2803739089","doi":"https://doi.org/10.1145/3229762.3229763","title":"Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe","display_name":"Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe","publication_year":2018,"publication_date":"2018-06-20","ids":{"openalex":"https://openalex.org/W2803739089","doi":"https://doi.org/10.1145/3229762.3229763","mag":"2803739089"},"language":"en","primary_location":{"id":"doi:10.1145/3229762.3229763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229762.3229763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning","raw_type":"proceedings-article"},"type":"preprint","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/A5102049601","display_name":"Jiong Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jiong Gong","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056650480","display_name":"Haihao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haihao Shen","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618997","display_name":"Guoming Zhang","orcid":"https://orcid.org/0000-0003-2123-8125"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guoming Zhang","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386594","display_name":"Xiaoli Liu","orcid":"https://orcid.org/0000-0002-9224-8649"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaoli Liu","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032345308","display_name":"Shane Li","orcid":"https://orcid.org/0009-0003-6810-7031"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shane Li","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436147","display_name":"Ge Jin","orcid":"https://orcid.org/0000-0002-9427-4023"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ge Jin","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088544980","display_name":"Niharika Maheshwari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Niharika Maheshwari","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024617712","display_name":"Evarist Fomenko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Evarist Fomenko","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038865838","display_name":"Eden Segal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eden Segal","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102049601"],"corresponding_institution_ids":["https://openalex.org/I4210158342"],"apc_list":null,"apc_paid":null,"fwci":2.31012063,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.88368864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958000183105469,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.8604640960693359},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7848077416419983},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7200394868850708},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6743946075439453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5997079014778137},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.570571780204773},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4395716190338135},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.43019622564315796},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.4232051968574524},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3242761492729187},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.10218170285224915},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08248540759086609}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8604640960693359},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7848077416419983},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7200394868850708},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6743946075439453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5997079014778137},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.570571780204773},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4395716190338135},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.43019622564315796},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.4232051968574524},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3242761492729187},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.10218170285224915},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08248540759086609},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3229762.3229763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229762.3229763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning","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":7,"referenced_works":["https://openalex.org/W1921523184","https://openalex.org/W2037227137","https://openalex.org/W2117539524","https://openalex.org/W2949117887","https://openalex.org/W2949605076","https://openalex.org/W2949650786","https://openalex.org/W3106250896"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W2055243143","https://openalex.org/W4313906399","https://openalex.org/W4321487865","https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3035501883"],"abstract_inverted_index":{"High":[0],"throughput":[1,81],"and":[2,42,82,87,93,104,107,122],"low":[3,39],"latency":[4,83],"inference":[5,24,41,80],"of":[6,15,26,46,72],"deep":[7,16,32],"neural":[8,48],"networks":[9,49],"are":[10,89],"critical":[11],"for":[12],"the":[13,22,28,70,79,123,129],"deployment":[14],"learning":[17,33],"applications.":[18],"This":[19],"paper":[20],"presents":[21],"efficient":[23,37],"techniques":[25,45,114],"IntelCaffe,":[27],"first":[29],"Intel(R)":[30,51],"optimized":[31,57],"framework":[34],"that":[35,78],"supports":[36],"8-bit":[38,56],"precision":[40],"model":[43,58,68],"optimization":[44],"convolutional":[47],"on":[50,118,131],"Xeon(R)":[52],"Scalable":[53],"Processors.":[54],"The":[55],"is":[59,125],"automatically":[60],"generated":[61],"with":[62,84,96],"a":[63],"calibration":[64],"process":[65],"from":[66,100,109],"FP32":[67,102],"without":[69],"need":[71],"fine-tuning":[73],"or":[74],"retraining.":[75],"We":[76],"show":[77],"ResNet-50,":[85],"Inception-v3":[86],"SSD":[88],"improved":[90],"by":[91,105],"1.38X-2.9X":[92],"1.35X-3X":[94],"respectively":[95],"neglectable":[97],"accuracy":[98],"loss":[99],"IntelCaffe":[101,119],"baseline":[103],"56X-75X":[106],"26X-37X":[108],"BVLC":[110],"Caffe.":[111],"All":[112],"these":[113],"have":[115],"been":[116],"open-sourced":[117],"GitHub":[120],"(https://github.com/intel/caffe),":[121],"artifact":[124],"provided":[126],"to":[127],"reproduce":[128],"result":[130],"Amazon":[132],"AWS":[133],"Cloud.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}