{"id":"https://openalex.org/W4385482620","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191309","title":"Knowledge Distillation with Deep Supervision","display_name":"Knowledge Distillation with Deep Supervision","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385482620","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191309"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191309","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5084098932","display_name":"Shiya Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiya Luo","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101821806","display_name":"Defang Chen","orcid":"https://orcid.org/0000-0003-0833-7401"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Defang Chen","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100428569","display_name":"Can Wang","orcid":"https://orcid.org/0000-0002-2259-1038"},"institutions":[{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]},{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Can Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou City University,Hangzhou,China","ZJU-Bangsun Joint Research Center, and Shanghai Institute for Advanced Study of Zhejiang University","Zhejiang University, Hangzhou City University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou City University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"ZJU-Bangsun Joint Research Center, and Shanghai Institute for Advanced Study of Zhejiang University","institution_ids":["https://openalex.org/I4210137766"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I4400573310","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3641,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65533993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9951000213623047,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9794999957084656,"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":0.7689594030380249},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7656946778297424},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6516872048377991},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6381321549415588},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5789692401885986},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5613345503807068},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.49557816982269287},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4760420322418213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4715718626976013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4629415273666382},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.18628811836242676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7689594030380249},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7656946778297424},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6516872048377991},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6381321549415588},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5789692401885986},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5613345503807068},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.49557816982269287},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4760420322418213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715718626976013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4629415273666382},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.18628811836242676},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191309","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[{"id":"https://openalex.org/G3792927286","display_name":null,"funder_award_id":"U1866602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1690739335","https://openalex.org/W1814328102","https://openalex.org/W1821462560","https://openalex.org/W1849277567","https://openalex.org/W2097117768","https://openalex.org/W2163605009","https://openalex.org/W2168894214","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2531409750","https://openalex.org/W2551176409","https://openalex.org/W2561238782","https://openalex.org/W2739879705","https://openalex.org/W2883780447","https://openalex.org/W2936864631","https://openalex.org/W2950014519","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963351448","https://openalex.org/W2963815618","https://openalex.org/W2964137095","https://openalex.org/W2966796096","https://openalex.org/W2982242214","https://openalex.org/W2987861506","https://openalex.org/W2988396473","https://openalex.org/W2995607862","https://openalex.org/W2996970889","https://openalex.org/W3034368386","https://openalex.org/W3106974277","https://openalex.org/W3108258117","https://openalex.org/W3118608800","https://openalex.org/W3127215335","https://openalex.org/W3138154797","https://openalex.org/W3174102142","https://openalex.org/W3202329792","https://openalex.org/W4281483168","https://openalex.org/W4281489207","https://openalex.org/W4295312788","https://openalex.org/W4312929415","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6639204139","https://openalex.org/W6684191040","https://openalex.org/W6684665197","https://openalex.org/W6697925102","https://openalex.org/W6713132643","https://openalex.org/W6728184133","https://openalex.org/W6745447533","https://openalex.org/W6753767121","https://openalex.org/W6761308216","https://openalex.org/W6766978945","https://openalex.org/W6769906912","https://openalex.org/W6783658810","https://openalex.org/W6787972765","https://openalex.org/W6839053282","https://openalex.org/W6842607031","https://openalex.org/W7061648608"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2768175398","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W32245304","https://openalex.org/W2953684491","https://openalex.org/W4285338581","https://openalex.org/W2015158429","https://openalex.org/W2080290893"],"abstract_inverted_index":{"Knowledge":[0,76],"distillation":[1],"aims":[2],"to":[3,33,91,108,120],"enhance":[4],"the":[5,14,24,35,39,43,59,88,93,111,123,140],"performance":[6],"of":[7,42,87,95,114,142],"a":[8,17],"lightweight":[9],"student":[10,44,52,97,124],"model":[11,90],"by":[12],"exploiting":[13],"knowledge":[15,26,67],"from":[16],"pre-trained":[18],"cumbersome":[19],"teacher":[20,28,89],"model.":[21],"However,":[22],"in":[23,49,58,106],"traditional":[25],"distillation,":[27],"predictions":[29,83],"are":[30],"only":[31],"used":[32],"provide":[34],"supervisory":[36],"signal":[37],"for":[38],"last":[40],"layer":[41],"model,":[45],"which":[46,79],"may":[47],"result":[48],"those":[50],"shallow":[51,96,116],"layers":[53],"lacking":[54],"accurate":[55],"training":[56,94],"guidance":[57],"layer-by-layer":[60],"back":[61],"propagation":[62],"and":[63,84,130],"thus":[64],"hinders":[65],"effective":[66],"transfer.":[68],"To":[69],"address":[70],"this":[71],"issue,":[72],"we":[73],"propose":[74],"Deeply-Supervised":[75],"Distillation":[77],"(DSKD),":[78],"fully":[80],"utilizes":[81],"class":[82],"feature":[85],"maps":[86],"supervise":[92],"layers.":[98],"A":[99],"loss-based":[100],"weight":[101],"allocation":[102],"strategy":[103],"is":[104,147],"developed":[105],"DSKD":[107],"adaptively":[109],"balance":[110],"learning":[112],"process":[113],"each":[115],"layer,":[117],"so":[118],"as":[119],"further":[121],"improve":[122],"performance.":[125],"Extensive":[126],"experiments":[127],"on":[128],"CIFAR-100":[129],"TinyImageNet":[131],"with":[132],"various":[133],"teacher-student":[134],"models":[135],"show":[136],"significantly":[137],"performance,":[138],"confirming":[139],"effectiveness":[141],"our":[143],"proposed":[144],"method.":[145],"Code":[146],"available":[148],"at:":[149],"https://github.com/luoshiya/DSKD":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}