{"id":"https://openalex.org/W2904181757","doi":"https://doi.org/10.1109/icce-berlin.2018.8576251","title":"CNN Inference: Dynamic and Predictive Quantization","display_name":"CNN Inference: Dynamic and Predictive Quantization","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2904181757","doi":"https://doi.org/10.1109/icce-berlin.2018.8576251","mag":"2904181757"},"language":"en","primary_location":{"id":"doi:10.1109/icce-berlin.2018.8576251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-berlin.2018.8576251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 8th International Conference on Consumer Electronics - Berlin (ICCE-Berlin)","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/A5009560883","display_name":"Kumar Desappan","orcid":null},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kumar Desappan","raw_affiliation_strings":["Automotive Processor Business \u2013 Texas Instruments India Ltd"],"affiliations":[{"raw_affiliation_string":"Automotive Processor Business \u2013 Texas Instruments India Ltd","institution_ids":["https://openalex.org/I74760111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044937170","display_name":"Mihir Mody","orcid":null},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihir Mody","raw_affiliation_strings":["Automotive Processor Business \u2013 Texas Instruments India Ltd"],"affiliations":[{"raw_affiliation_string":"Automotive Processor Business \u2013 Texas Instruments India Ltd","institution_ids":["https://openalex.org/I74760111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103701595","display_name":"Manu Mathew","orcid":"https://orcid.org/0000-0003-1692-0058"},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manu Mathew","raw_affiliation_strings":["Automotive Processor Business \u2013 Texas Instruments India Ltd"],"affiliations":[{"raw_affiliation_string":"Automotive Processor Business \u2013 Texas Instruments India Ltd","institution_ids":["https://openalex.org/I74760111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031543620","display_name":"Pramod Swami","orcid":null},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pramod Swami","raw_affiliation_strings":["Automotive Processor Business \u2013 Texas Instruments India Ltd"],"affiliations":[{"raw_affiliation_string":"Automotive Processor Business \u2013 Texas Instruments India Ltd","institution_ids":["https://openalex.org/I74760111"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079155469","display_name":"Praveen Eppa","orcid":null},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Praveen Eppa","raw_affiliation_strings":["Automotive Processor Business \u2013 Texas Instruments India Ltd"],"affiliations":[{"raw_affiliation_string":"Automotive Processor Business \u2013 Texas Instruments India Ltd","institution_ids":["https://openalex.org/I74760111"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009560883"],"corresponding_institution_ids":["https://openalex.org/I74760111"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.14895715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9972000122070312,"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":0.7646596431732178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7431516647338867},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6349194049835205},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6078836917877197},{"id":"https://openalex.org/keywords/automotive-industry","display_name":"Automotive industry","score":0.5377687811851501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157347321510315},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5066138505935669},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.49689581990242004},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.48252245783805847},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4789084196090698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4165743589401245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37462711334228516},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11847788095474243}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7646596431732178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7431516647338867},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6349194049835205},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6078836917877197},{"id":"https://openalex.org/C526921623","wikidata":"https://www.wikidata.org/wiki/Q190117","display_name":"Automotive industry","level":2,"score":0.5377687811851501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157347321510315},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5066138505935669},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.49689581990242004},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.48252245783805847},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4789084196090698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4165743589401245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37462711334228516},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11847788095474243},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/icce-berlin.2018.8576251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-berlin.2018.8576251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 8th International Conference on Consumer Electronics - Berlin (ICCE-Berlin)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1825672851","https://openalex.org/W2097117768","https://openalex.org/W2125186487","https://openalex.org/W2163605009","https://openalex.org/W2286365479","https://openalex.org/W2337344472","https://openalex.org/W2737244778","https://openalex.org/W2963122961","https://openalex.org/W4294371482","https://openalex.org/W6637373629","https://openalex.org/W6638839971","https://openalex.org/W6684191040","https://openalex.org/W6696004547","https://openalex.org/W6703414193","https://openalex.org/W6746698991"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"techniques":[2],"like":[3],"Convolutional":[4],"Neural":[5],"Networks":[6],"(CNN)":[7],"are":[8],"the":[9,39,81,102,166],"de-facto":[10],"method":[11],"for":[12,83],"image":[13],"classification":[14],"with":[15],"broad":[16],"usage":[17],"spanning":[18],"across":[19,45,153],"automotive,":[20],"industrial,":[21],"medicine,":[22],"robotics":[23],"etc.":[24],"Efficient":[25],"implementation":[26],"of":[27,125,165],"CNN":[28],"inference":[29,107],"on":[30,121,138],"embedded":[31,126],"device":[32],"requires":[33],"a":[34,67],"quantization":[35,69,92,111],"method,":[36],"which":[37],"minimizes":[38],"accuracy":[40,96,143],"loss,":[41],"ability":[42],"to":[43,71,90,94,109],"generalize":[44],"deployment":[46,155],"scenarios":[47,156],"as":[48,50],"well":[49,152],"real-time":[51,114],"processing.":[52],"Existing":[53],"literature":[54],"doesn't":[55],"address":[56],"all":[57],"these":[58],"three":[59],"requirements":[60],"simultaneously.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"novel":[68],"algorithm":[70],"overcome":[72],"above":[73],"mentioned":[74],"challenges.":[75],"The":[76,98,116,129,149],"proposed":[77,99,117,130],"solution":[78,100,118,131,150],"dynamically":[79],"selects":[80],"scale":[82,93],"quantizing":[84],"activations":[85],"and":[86],"uses":[87],"Kalman":[88],"filter":[89],"predict":[91],"reduce":[95],"loss.":[97],"exploits":[101],"range":[103],"statistics":[104],"from":[105],"previous":[106],"processes":[108],"estimate":[110],"scale,":[112],"enabling":[113],"solution.":[115,167],"is":[119,132],"implemented":[120],"TI's":[122],"TDA":[123],"family":[124],"automotive":[127],"processors.":[128],"running":[133],"real":[134],"time":[135],"semantic":[136],"segmentation":[137],"TDA2x":[139],"processor":[140],"within":[141],"0.1%":[142],"loss":[144],"compared":[145],"floating":[146],"point":[147],"algorithm.":[148],"performs":[151],"multiple":[154],"(e.g.":[157],"rain,":[158],"snow,":[159],"night":[160],"etc)":[161],"demonstrating":[162],"generalization":[163],"capability":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}