{"id":"https://openalex.org/W2964622438","doi":"https://doi.org/10.24963/ijcai.2019/416","title":"Learning Instance-wise Sparsity for Accelerating Deep Models","display_name":"Learning Instance-wise Sparsity for Accelerating Deep Models","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964622438","doi":"https://doi.org/10.24963/ijcai.2019/416","mag":"2964622438"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/416","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/416","pdf_url":"https://www.ijcai.org/proceedings/2019/0416.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0416.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031128205","display_name":"Chuanjian Liu","orcid":"https://orcid.org/0009-0001-8543-7732"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Chuanjian Liu","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727358","display_name":"Yunhe Wang","orcid":"https://orcid.org/0000-0002-2709-4946"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yunhe Wang","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784732","display_name":"Kai Han","orcid":"https://orcid.org/0000-0002-9761-2702"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Kai Han","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101082712","display_name":"Chunjing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["AU","SE"],"is_corresponding":false,"raw_author_name":"Chunjing Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab","School of Computer Science, FEIT, University of Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"School of Computer Science, FEIT, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001529504","display_name":"Chang Xu","orcid":"https://orcid.org/0000-0002-4756-0609"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["AU","SE"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab","School of Computer Science, FEIT, University of Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"School of Computer Science, FEIT, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3001","last_page":"3007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.994700014591217,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.994700014591217,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9858999848365784,"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":0.9853000044822693,"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":0.8132423162460327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7315651178359985},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6498931050300598},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6308212876319885},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.627586841583252},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.595488429069519},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5816556215286255},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.55954909324646},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5478801131248474},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5357367992401123},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5130704641342163},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4577329456806183},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43562692403793335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132423162460327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7315651178359985},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6498931050300598},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6308212876319885},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.627586841583252},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.595488429069519},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5816556215286255},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.55954909324646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5478801131248474},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5357367992401123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130704641342163},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4577329456806183},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43562692403793335},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/416","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/416","pdf_url":"https://www.ijcai.org/proceedings/2019/0416.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/416","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/416","pdf_url":"https://www.ijcai.org/proceedings/2019/0416.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4651944327","display_name":"Multi-view synergistic learning for human behaviour analysis","funder_award_id":"DE180101438","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964622438.pdf","grobid_xml":"https://content.openalex.org/works/W2964622438.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W587794757","https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W2009501510","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2242218935","https://openalex.org/W2300242332","https://openalex.org/W2554242204","https://openalex.org/W2604998962","https://openalex.org/W2739542029","https://openalex.org/W2752037867","https://openalex.org/W2798722023","https://openalex.org/W2806990599","https://openalex.org/W2896006880","https://openalex.org/W2950248853","https://openalex.org/W2952179044","https://openalex.org/W2952922798","https://openalex.org/W2962677625","https://openalex.org/W2962851801","https://openalex.org/W2962935523","https://openalex.org/W2963000224","https://openalex.org/W2963163009","https://openalex.org/W2963393494","https://openalex.org/W2963518064","https://openalex.org/W2963896595","https://openalex.org/W2964233199","https://openalex.org/W3118608800","https://openalex.org/W4294557928","https://openalex.org/W4297813615"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2373300491","https://openalex.org/W1212596013","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W3042419602","https://openalex.org/W2966649771","https://openalex.org/W2294590153","https://openalex.org/W4220659530"],"abstract_inverted_index":{"Exploring":[0],"deep":[1,30,88],"convolutional":[2],"neural":[3,89,115],"networks":[4,90,150],"of":[5,19,24,84,105,112,129,154],"high":[6],"efficiency":[7],"and":[8,41,149],"low":[9],"memory":[10],"usage":[11],"is":[12,63],"very":[13],"essential":[14],"for":[15,69,141],"a":[16,50,75,113,132],"wide":[17],"variety":[18],"machine":[20],"learning":[21],"tasks.":[22],"Most":[23],"existing":[25],"approaches":[26],"used":[27],"to":[28,91,120,134],"accelerate":[29,121],"models":[31],"by":[32,53,65,73,109],"manipulating":[33],"parameters":[34],"or":[35],"filters":[36],"without":[37],"data,":[38],"e.g.,":[39],"pruning":[40,62],"decomposition.":[42],"In":[43],"contrast,":[44],"we":[45,79],"study":[46],"this":[47],"problem":[48],"from":[49],"different":[51,70],"perspective":[52],"respecting":[54],"the":[55,96,122,136,152,155],"difference":[56],"between":[57],"data.":[58],"An":[59],"instance-wise":[60],"feature":[61,76,82],"developed":[64],"identifying":[66],"informative":[67],"features":[68,104],"instances.":[71],"Specifically,":[72],"investigating":[74],"decay":[77],"regularization,":[78],"expect":[80],"intermediate":[81,110],"maps":[83],"each":[85],"instance":[86],"in":[87],"be":[92,118],"sparse":[93],"while":[94],"preserving":[95],"overall":[97],"network":[98,116],"performance.":[99],"During":[100],"online":[101],"inference,":[102],"subtle":[103],"input":[106],"images":[107],"extracted":[108],"layers":[111,137],"well-trained":[114],"can":[117],"eliminated":[119],"subsequent":[123],"calculations.":[124],"We":[125],"further":[126],"take":[127],"coefficient":[128],"variation":[130],"as":[131],"measure":[133],"select":[135],"that":[138],"are":[139],"appropriate":[140],"acceleration.":[142],"Extensive":[143],"experiments":[144],"conducted":[145],"on":[146],"benchmark":[147],"datasets":[148],"demonstrate":[151],"effectiveness":[153],"proposed":[156],"method.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}