{"id":"https://openalex.org/W3197292393","doi":"https://doi.org/10.1109/iwqos52092.2021.9521267","title":"Neuron Manifold Distillation for Edge Deep Learning","display_name":"Neuron Manifold Distillation for Edge Deep Learning","publication_year":2021,"publication_date":"2021-06-25","ids":{"openalex":"https://openalex.org/W3197292393","doi":"https://doi.org/10.1109/iwqos52092.2021.9521267","mag":"3197292393"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos52092.2021.9521267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos52092.2021.9521267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM 29th International Symposium on Quality of Service (IWQOS)","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/A5031701370","display_name":"Zeyi Tao","orcid":"https://orcid.org/0000-0002-7925-0891"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyi Tao","raw_affiliation_strings":["Department of Computer Science, William & Mary, Williamsburg, Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, William & Mary, Williamsburg, Virginia","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579220","display_name":"Qi Xia","orcid":"https://orcid.org/0000-0002-5096-3329"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Xia","raw_affiliation_strings":["Department of Computer Science, William & Mary, Williamsburg, Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, William & Mary, Williamsburg, Virginia","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100426184","display_name":"Qun Li","orcid":"https://orcid.org/0000-0003-2231-6615"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qun Li","raw_affiliation_strings":["Department of Computer Science, William & Mary, Williamsburg, Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, William & Mary, Williamsburg, Virginia","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.191,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5039604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7393126487731934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.723161518573761},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6043464541435242},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5753864645957947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740986466407776},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5684618949890137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5503862500190735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48303040862083435},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47853025794029236},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44838523864746094},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16247814893722534},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15019476413726807}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7393126487731934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723161518573761},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6043464541435242},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5753864645957947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740986466407776},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5684618949890137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5503862500190735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48303040862083435},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47853025794029236},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44838523864746094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16247814893722534},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15019476413726807},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos52092.2021.9521267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos52092.2021.9521267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM 29th International Symposium on Quality of Service (IWQOS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1595132914","https://openalex.org/W1686810756","https://openalex.org/W1690739335","https://openalex.org/W1724438581","https://openalex.org/W1821462560","https://openalex.org/W2053186076","https://openalex.org/W2131524184","https://openalex.org/W2155008293","https://openalex.org/W2167215970","https://openalex.org/W2172166488","https://openalex.org/W2194775991","https://openalex.org/W2260663238","https://openalex.org/W2285660444","https://openalex.org/W2319920447","https://openalex.org/W2401985367","https://openalex.org/W2541993794","https://openalex.org/W2561238782","https://openalex.org/W2594672382","https://openalex.org/W2626089772","https://openalex.org/W2731516819","https://openalex.org/W2739879705","https://openalex.org/W2883929540","https://openalex.org/W2885079409","https://openalex.org/W2885829265","https://openalex.org/W2904819746","https://openalex.org/W2950248853","https://openalex.org/W2952432176","https://openalex.org/W2962734330","https://openalex.org/W2963048316","https://openalex.org/W2963674932","https://openalex.org/W2963910545","https://openalex.org/W2964118293","https://openalex.org/W2964223234","https://openalex.org/W2965921687","https://openalex.org/W2989368243","https://openalex.org/W3034368386","https://openalex.org/W3095947931","https://openalex.org/W3107994934","https://openalex.org/W3137762252","https://openalex.org/W4295364049","https://openalex.org/W6635542370","https://openalex.org/W6637373629","https://openalex.org/W6637551013","https://openalex.org/W6637709462","https://openalex.org/W6638523607","https://openalex.org/W6638632666","https://openalex.org/W6679667936","https://openalex.org/W6682989981","https://openalex.org/W6684563725","https://openalex.org/W6685405536","https://openalex.org/W6692521979","https://openalex.org/W6712771190","https://openalex.org/W6728994542","https://openalex.org/W6730179637","https://openalex.org/W6734203436","https://openalex.org/W6739475399","https://openalex.org/W6740493225","https://openalex.org/W6753380695","https://openalex.org/W6753492755","https://openalex.org/W6753991380","https://openalex.org/W6779590286","https://openalex.org/W7002073801"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W1212596013","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581","https://openalex.org/W4229439743","https://openalex.org/W4205547277"],"abstract_inverted_index":{"Although":[0],"deep":[1],"neural":[2],"networks":[3],"show":[4],"their":[5,31],"extraordinary":[6],"power":[7],"in":[8,148],"various":[9],"object":[10],"detection":[11],"tasks,":[12],"it":[13],"is":[14],"very":[15],"challenging":[16],"for":[17,151],"them":[18],"to":[19,30,67],"be":[20],"deployed":[21],"on":[22],"resource":[23],"constrained":[24],"devices":[25],"or":[26,41],"embedded":[27],"systems":[28],"due":[29],"high":[32],"computational":[33,79],"cost.":[34],"Efforts":[35],"such":[36],"as":[37],"model":[38,60,65,72],"partition,":[39],"pruning":[40],"quantization":[42],"have":[43],"been":[44],"used":[45],"at":[46,58],"an":[47],"expense":[48],"of":[49,116],"accuracy":[50],"loss.":[51],"Recently":[52],"proposed":[53,142],"knowledge":[54,61],"distillation":[55,97,135],"(KD)":[56],"aims":[57],"transferring":[59],"from":[62],"a":[63,68,93,122,145],"well-trained":[64],"(teacher)":[66],"smaller":[69],"and":[70,83,125,140],"faster":[71],"(student),":[73],"which":[74],"can":[75],"significantly":[76],"reduce":[77],"the":[78,85,100,112,117,141,152],"cost,":[80],"memory":[81],"usage,":[82],"prolong":[84],"battery":[86],"lifetime.":[87],"In":[88],"this":[89],"work,":[90],"we":[91],"propose":[92],"novel":[94],"neuron":[95],"manifold":[96],"(NMD),":[98],"where":[99],"student":[101,127],"models":[102],"not":[103],"only":[104],"imitate":[105],"teacher\u2019s":[106],"output":[107],"activations,":[108],"but":[109],"also":[110],"learn":[111],"feature":[113],"geometry":[114],"structure":[115],"teacher.":[118],"Our":[119],"approach":[120],"produces":[121],"high-quality,":[123],"compact,":[124],"lightweight":[126],"model.":[128,154],"We":[129],"conduct":[130],"comprehensive":[131],"experiments":[132],"with":[133],"different":[134],"configurations":[136],"over":[137],"multiple":[138],"datasets,":[139],"method":[143],"demonstrates":[144],"consistent":[146],"improvement":[147],"accuracy-speed":[149],"trade-offs":[150],"distilled":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}