{"id":"https://openalex.org/W3035732661","doi":"https://doi.org/10.24963/ijcai.2020/363","title":"Feature Statistics Guided Efficient Filter Pruning","display_name":"Feature Statistics Guided Efficient Filter Pruning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035732661","doi":"https://doi.org/10.24963/ijcai.2020/363","mag":"3035732661"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/363","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/363","pdf_url":"https://www.ijcai.org/proceedings/2020/0363.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0363.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100455129","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-1230-4007"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hang Li","raw_affiliation_strings":["School of Computer Science, McGill University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410908","display_name":"Chen Ma","orcid":"https://orcid.org/0000-0001-7933-9813"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chen Ma","raw_affiliation_strings":["School of Computer Science, McGill University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070905937","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-7044-3232"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100372152","display_name":"Xue Liu","orcid":"https://orcid.org/0000-0001-5252-3442"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xue Liu","raw_affiliation_strings":["School of Computer Science, McGill University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100455129"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":1.7586,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87068966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2619","last_page":"2625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9975000023841858,"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":0.743408203125},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6392796039581299},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6300927400588989},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6269636154174805},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.604263424873352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.575772762298584},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5523216128349304},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.545593798160553},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5362251400947571},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.45735588669776917},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4451161324977875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.360032320022583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07270070910453796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743408203125},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6392796039581299},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6300927400588989},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6269636154174805},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.604263424873352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.575772762298584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5523216128349304},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.545593798160553},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5362251400947571},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.45735588669776917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4451161324977875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.360032320022583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07270070910453796},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/363","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/363","pdf_url":"https://www.ijcai.org/proceedings/2020/0363.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/363","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/363","pdf_url":"https://www.ijcai.org/proceedings/2020/0363.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035732661.pdf","grobid_xml":"https://content.openalex.org/works/W3035732661.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1832693441","https://openalex.org/W2102605133","https://openalex.org/W2134797427","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2495425901","https://openalex.org/W2800705832","https://openalex.org/W2803543130","https://openalex.org/W2896409484","https://openalex.org/W2905031717","https://openalex.org/W2928560789","https://openalex.org/W2949941638","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963363373","https://openalex.org/W2963981420","https://openalex.org/W2964233199","https://openalex.org/W2965174861","https://openalex.org/W2984618279","https://openalex.org/W3118608800","https://openalex.org/W4297775537"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W4280599700","https://openalex.org/W3183570023","https://openalex.org/W4382323155","https://openalex.org/W2016508734","https://openalex.org/W4287067436","https://openalex.org/W3188310744"],"abstract_inverted_index":{"Building":[0],"compact":[1],"convolutional":[2],"neural":[3],"networks":[4],"(CNNs)":[5],"with":[6,97,109,116,141],"reliable":[7],"performance":[8],"is":[9],"a":[10,23,56,72],"critical":[11],"but":[12],"challenging":[13],"task,":[14],"especially":[15],"when":[16],"deploying":[17],"them":[18],"in":[19,55],"real-world":[20],"applications.":[21],"As":[22],"common":[24],"approach":[25],"to":[26,41,94,133],"reduce":[27],"the":[28,37,52,61],"size":[29],"of":[30,36,81],"CNNs,":[31],"pruning":[32,75],"methods":[33,49],"delete":[34],"part":[35],"CNN":[38,118],"filters":[39],"according":[40],"some":[42],"metrics":[43],"such":[44],"as":[45],"l1-norm.":[46],"However,":[47],"previous":[48],"hardly":[50],"leverage":[51],"information":[53,99],"variance":[54],"single":[57],"feature":[58,65,82],"map":[59,83],"and":[60,88,137],"similarity":[62],"characteristics":[63],"among":[64],"maps.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"propose":[71],"novel":[73],"filter":[74],"method,":[76],"which":[77],"incorporates":[78],"two":[79],"kinds":[80],"selections:":[84],"diversity-aware":[85],"selection":[86,90],"(DFS)":[87],"similarity-aware":[89],"(SFS).":[91],"DFS":[92],"aims":[93],"discover":[95],"features":[96,104],"low":[98],"diversity":[100],"while":[101],"SFS":[102],"removes":[103],"that":[105,128],"have":[106],"high":[107],"similarities":[108],"others.":[110],"We":[111],"conduct":[112],"extensive":[113],"empirical":[114],"experiments":[115],"various":[117],"architectures":[119],"on":[120],"publicly":[121],"available":[122],"datasets.":[123],"The":[124],"experimental":[125],"results":[126],"demonstrate":[127],"our":[129],"model":[130],"obtains":[131],"up":[132],"91.6%":[134],"parameter":[135],"decrease":[136],"83.7%":[138],"FLOPs":[139],"reduction":[140],"almost":[142],"no":[143],"accuracy":[144],"loss.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}