{"id":"https://openalex.org/W3029513528","doi":"https://doi.org/10.1145/3387168.3387184","title":"Automatic Compression Ratio Allocation for Pruning Convolutional Neural Networks","display_name":"Automatic Compression Ratio Allocation for Pruning Convolutional Neural Networks","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W3029513528","doi":"https://doi.org/10.1145/3387168.3387184","mag":"3029513528"},"language":"en","primary_location":{"id":"doi:10.1145/3387168.3387184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3387168.3387184","pdf_url":null,"source":{"id":"https://openalex.org/S4306523820","display_name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","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/A5100357488","display_name":"Yunfeng Liu","orcid":"https://orcid.org/0000-0003-0793-7739"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfeng Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024889670","display_name":"Huihui Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihui Kong","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051061888","display_name":"Peihua Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peihua Yu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.366,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6861206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9983000159263611,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8099671602249146},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7892070412635803},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7824576497077942},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.7076941728591919},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7053279876708984},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5525288581848145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4673234522342682},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4508514106273651},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4414230287075043},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.42978155612945557},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4286530613899231},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3968196213245392},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32323551177978516},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.2244878113269806},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.18816789984703064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10261234641075134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099671602249146},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7892070412635803},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7824576497077942},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.7076941728591919},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7053279876708984},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5525288581848145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4673234522342682},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4508514106273651},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4414230287075043},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.42978155612945557},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4286530613899231},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3968196213245392},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32323551177978516},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2244878113269806},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.18816789984703064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10261234641075134},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3387168.3387184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3387168.3387184","pdf_url":null,"source":{"id":"https://openalex.org/S4306523820","display_name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.49000000953674316,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1690739335","https://openalex.org/W1745334888","https://openalex.org/W1903029394","https://openalex.org/W2163605009","https://openalex.org/W2300242332","https://openalex.org/W2515385951","https://openalex.org/W2613718673","https://openalex.org/W2707890836","https://openalex.org/W2750784772","https://openalex.org/W2787752464","https://openalex.org/W2894994475","https://openalex.org/W2928560789","https://openalex.org/W2963419583","https://openalex.org/W2963674932","https://openalex.org/W2964233199"],"related_works":["https://openalex.org/W3005814217","https://openalex.org/W2768628697","https://openalex.org/W1973200086","https://openalex.org/W1965503293","https://openalex.org/W2388481516","https://openalex.org/W2088378984","https://openalex.org/W2356662348","https://openalex.org/W2386366915","https://openalex.org/W4220868150","https://openalex.org/W2141840609"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,105],"networks":[2],"(CNNs)":[3],"have":[4,21,33],"demonstrated":[5],"significant":[6],"performance":[7],"improvement":[8],"in":[9],"many":[10],"application":[11,24],"scenarios.":[12],"However,":[13],"the":[14,26,53,122,141,157,183],"high":[15,178],"computational":[16],"complexity":[17],"and":[18,28,55,79,165],"model":[19],"size":[20],"limited":[22],"its":[23],"on":[25,76,98,136,156,185],"mobile":[27],"embedded":[29],"devices.":[30],"Various":[31],"approaches":[32,63],"been":[34],"proposed":[35],"to":[36,65,82,102,126,152,159],"compress":[37],"CNNs.":[38],"Filter":[39],"pruning":[40,119,146],"is":[41,130],"widely":[42],"considered":[43],"as":[44],"a":[45,177],"promising":[46],"solution,":[47],"which":[48,73,129],"can":[49,171],"significantly":[50,174],"speed":[51],"up":[52],"inference":[54],"reduce":[56,172,189],"memory":[57],"consumption.":[58],"To":[59],"this":[60,86],"end,":[61],"most":[62],"tend":[64],"prune":[66,103],"filters":[67],"by":[68,132],"manually":[69],"allocating":[70,113],"compression":[71,114,124,150],"ratio,":[72],"highly":[74],"relies":[75],"individual":[77],"expertise":[78],"not":[80],"friendly":[81],"non-professional":[83],"users.":[84],"In":[85],"paper,":[87],"we":[88,188],"propose":[89],"an":[90],"Automatic":[91],"Compression":[92],"Ratio":[93],"Allocation":[94],"(ACRA)":[95],"scheme":[96,170],"based":[97,135,155],"binary":[99,133],"search":[100,134],"algorithm":[101],"convolutional":[104],"networks.":[106,143],"Specifically,":[107,181],"ACRA":[108],"provides":[109],"two":[110],"strategies":[111],"for":[112,182],"ratio":[115,125,151],"automatically.":[116],"First,":[117],"uniform":[118],"strategy":[120,147],"allocates":[121,148],"same":[123],"each":[127,153],"layer,":[128],"obtained":[131],"target":[137],"FLOPs":[138,173,191],"reduction":[139],"of":[140],"whole":[142],"Second,":[144],"sensitivity-based":[145],"appropriate":[149],"layer":[154],"sensitivity":[158],"accuracy.":[160],"Experimental":[161],"results":[162],"from":[163],"VGG11":[164],"VGG-16,":[166],"demonstrate":[167],"that":[168],"our":[169],"while":[175],"maintaining":[176],"accuracy":[179,195],"level.":[180],"VGG16":[184],"CIFAR-10":[186],"dataset,":[187],"29.18%":[190],"with":[192],"only":[193],"1.24%":[194],"decrease.":[196]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}