{"id":"https://openalex.org/W4415068071","doi":"https://doi.org/10.48550/arxiv.2506.11093","title":"EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices","display_name":"EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices","publication_year":2025,"publication_date":"2025-06-05","ids":{"openalex":"https://openalex.org/W4415068071","doi":"https://doi.org/10.48550/arxiv.2506.11093"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.11093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11093","pdf_url":"https://arxiv.org/pdf/2506.11093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022196006","display_name":"Shaibal Saha","orcid":"https://orcid.org/0009-0003-5065-1581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saha, Shaibal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071690223","display_name":"Lanyu Xu","orcid":"https://orcid.org/0000-0003-3442-8411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Lanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9440000057220459,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9440000057220459,"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":0.6995000243186951},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5223000049591064},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47690001130104065},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.36320000886917114},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.35370001196861267}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6995000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.617900013923645},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5223000049591064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5019999742507935},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47690001130104065},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.11093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11093","pdf_url":"https://arxiv.org/pdf/2506.11093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.11093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.11093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.11093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11093","pdf_url":"https://arxiv.org/pdf/2506.11093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hybrid":[0],"models":[1,35],"that":[2,46],"combine":[3],"convolutional":[4,51],"and":[5,53,81],"transformer":[6,57],"blocks":[7,52],"offer":[8],"strong":[9],"performance":[10],"in":[11],"computer":[12],"vision":[13],"(CV)":[14],"tasks":[15],"but":[16],"are":[17],"resource-intensive":[18],"for":[19,90],"edge":[20,85],"deployment.":[21,92],"Although":[22],"post-training":[23],"quantization":[24,49,55],"(PTQ)":[25],"can":[26],"help":[27],"reduce":[28],"resource":[29],"demand,":[30],"its":[31],"application":[32],"to":[33,50,56],"hybrid":[34],"remains":[36],"limited.":[37],"We":[38],"propose":[39],"EfficientQuant,":[40],"a":[41],"novel":[42],"structure-aware":[43],"PTQ":[44],"approach":[45],"applies":[47],"uniform":[48],"$log_2$":[54],"blocks.":[58],"EfficientQuant":[59],"achieves":[60],"$2.5":[61],"\\times":[62],"-":[63],"8.7":[64],"\\times$":[65],"latency":[66,80],"reduction":[67],"with":[68],"minimal":[69],"accuracy":[70],"loss":[71],"on":[72,84],"the":[73],"ImageNet-1K":[74],"dataset.":[75],"It":[76],"further":[77],"demonstrates":[78],"low":[79],"memory":[82],"efficiency":[83],"devices,":[86],"making":[87],"it":[88],"practical":[89],"real-world":[91]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-11T00:00:00"}