{"id":"https://openalex.org/W3163782850","doi":"https://doi.org/10.1109/icpr48806.2021.9412760","title":"Channel Planting for Deep Neural Networks using Knowledge Distillation","display_name":"Channel Planting for Deep Neural Networks using Knowledge Distillation","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3163782850","doi":"https://doi.org/10.1109/icpr48806.2021.9412760","mag":"3163782850"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5046417869","display_name":"Kakeru Mitsuno","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kakeru Mitsuno","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi Hiroshima, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014224994","display_name":"Yuichiro Nomura","orcid":"https://orcid.org/0000-0003-2716-1608"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichiro Nomura","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi Hiroshima, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086456461","display_name":"Takio Kurita","orcid":"https://orcid.org/0000-0003-3982-6750"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takio Kurita","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi Hiroshima, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113306721"],"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":"7573","last_page":"7579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9941999912261963,"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/distillation","display_name":"Distillation","score":0.649033784866333},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6388139128684998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5996268391609192},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5058967471122742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46137556433677673},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2887958586215973},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.15831926465034485},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.09336915612220764}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.649033784866333},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6388139128684998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996268391609192},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5058967471122742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46137556433677673},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2887958586215973},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.15831926465034485},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.09336915612220764}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2097117768","https://openalex.org/W2114766824","https://openalex.org/W2125389748","https://openalex.org/W2134797427","https://openalex.org/W2194775991","https://openalex.org/W2520760693","https://openalex.org/W2553303224","https://openalex.org/W2554931888","https://openalex.org/W2618530766","https://openalex.org/W2620998106","https://openalex.org/W2707890836","https://openalex.org/W2773706593","https://openalex.org/W2786031241","https://openalex.org/W2786054724","https://openalex.org/W2807961551","https://openalex.org/W2808168148","https://openalex.org/W2810075754","https://openalex.org/W2905741102","https://openalex.org/W2928560789","https://openalex.org/W2945908221","https://openalex.org/W2951104886","https://openalex.org/W2960010704","https://openalex.org/W2962746461","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963382930","https://openalex.org/W2963446712","https://openalex.org/W2963536136","https://openalex.org/W2963674932","https://openalex.org/W2963766446","https://openalex.org/W2963828549","https://openalex.org/W2963919236","https://openalex.org/W2964001144","https://openalex.org/W2964081807","https://openalex.org/W2964118293","https://openalex.org/W2964259004","https://openalex.org/W2965658867","https://openalex.org/W2965862774","https://openalex.org/W2967733054","https://openalex.org/W3013024145","https://openalex.org/W3089835766","https://openalex.org/W3097795029","https://openalex.org/W3105248137","https://openalex.org/W3163108002","https://openalex.org/W4300687381","https://openalex.org/W4302613003","https://openalex.org/W6638523607","https://openalex.org/W6674914833","https://openalex.org/W6677103964","https://openalex.org/W6678583879","https://openalex.org/W6679909955","https://openalex.org/W6684191040","https://openalex.org/W6687483927","https://openalex.org/W6725543821","https://openalex.org/W6730382033","https://openalex.org/W6741047420","https://openalex.org/W6746693648","https://openalex.org/W6757036269","https://openalex.org/W6763207085","https://openalex.org/W6786572489"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"In":[0,119],"recent":[1],"years,":[2],"deeper":[3,63,191],"and":[4,27,50,64,192,201,217,242],"wider":[5,65,193],"neural":[6,131],"networks":[7,40,66,100,115,132,165,199],"have":[8,31],"shown":[9],"excellent":[10],"performance":[11,71,155,232],"in":[12,23],"computer":[13],"vision":[14],"tasks,":[15],"while":[16,166],"their":[17],"enormous":[18],"amount":[19,250],"of":[20,38,62,72,98,149,162,190,207,251],"parameters":[21,52,150,171,236],"results":[22],"increased":[24],"computational":[25],"cost":[26],"overfitting.":[28],"Several":[29],"methods":[30,79],"been":[32,90],"proposed":[33,209],"to":[34,67,101,113,160,229,238],"compress":[35],"the":[36,39,60,73,83,96,99,103,142,153,163,168,177,183,188,198,205,208,220,239,244,252],"size":[37],"without":[41],"reducing":[42],"network":[43,75,144,154,241],"performance.":[44],"Network":[45],"pruning":[46],"can":[47,58,93,140,196],"reduce":[48,243],"redundant":[49],"unnecessary":[51],"from":[53],"a":[54,109,124,248],"network.":[55,85],"Knowledge":[56],"distillation":[57,179],"transfer":[59],"knowledge":[61,178,189],"smaller":[68,74,147],"networks.":[69],"The":[70],"obtained":[76],"by":[77,82,156,247],"these":[78],"is":[80,108],"bounded":[81],"predefined":[84],"Neural":[86],"architecture":[87,97,145],"search":[88,94,141],"has":[89],"proposed,":[91],"which":[92],"automatically":[95],"break":[102],"structure":[104],"limitation.":[105],"Also,":[106,173],"there":[107],"dynamic":[110],"configuration":[111],"method":[112,180,210],"train":[114],"incrementally":[116,159],"as":[117,215],"sub-networks.":[118],"this":[120],"paper,":[121],"we":[122,174,195,223,226],"present":[123],"novel":[125],"incremental":[126],"training":[127,182],"algorithm":[128],"for":[129,151,181],"deep":[130],"called":[133],"<i":[134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u201cplanting\u201d</i>":[136],".":[137],"Our":[138],"planting":[139],"optimal":[143],"with":[146,233],"number":[148],"improving":[152],"augmenting":[157],"channels":[158,184],"layers":[161],"initial":[164],"keeping":[167],"earlier":[169],"trained":[170],"fixed.":[172],"propose":[175],"using":[176],"planted.":[185],"By":[186],"transferring":[187],"networks,":[194],"grow":[197],"effectively":[200],"efficiently.":[202],"We":[203],"evaluate":[204],"effectiveness":[206],"on":[211],"different":[212],"datasets":[213],"such":[214],"CIFAR-10/100":[216],"STL-10.":[218],"For":[219],"STL-10":[221],"dataset,":[222],"show":[224],"that":[225],"are":[227],"able":[228],"achieve":[230],"comparable":[231],"only":[234],"7%":[235],"compared":[237],"larger":[240],"overfitting":[245],"caused":[246],"small":[249],"data.":[253]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}