{"id":"https://openalex.org/W3163781913","doi":"https://doi.org/10.1109/icassp39728.2021.9414674","title":"Robustness and Diversity Seeking Data-Free Knowledge Distillation","display_name":"Robustness and Diversity Seeking Data-Free Knowledge Distillation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163781913","doi":"https://doi.org/10.1109/icassp39728.2021.9414674","mag":"3163781913"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5066133603","display_name":"Pengchao Han","orcid":"https://orcid.org/0000-0003-2246-7640"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengchao Han","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027907258","display_name":"Jihong Park","orcid":"https://orcid.org/0000-0001-7623-6552"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jihong Park","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443968","display_name":"Shiqiang Wang","orcid":"https://orcid.org/0000-0003-2090-5512"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqiang Wang","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055203561","display_name":"Yejun Liu","orcid":"https://orcid.org/0000-0002-6398-7143"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yejun Liu","raw_affiliation_strings":["School of Comm. & Inf. Engineering, Chongqing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"School of Comm. & Inf. Engineering, Chongqing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066133603"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.9607,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76985294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2740","last_page":"2744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9969000220298767,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8108994364738464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6634779572486877},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6358685493469238},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.595664381980896},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4185718297958374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41668957471847534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3815975785255432},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3252394199371338},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.26163941621780396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20667552947998047},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.135199636220932}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8108994364738464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6634779572486877},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6358685493469238},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.595664381980896},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4185718297958374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41668957471847534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3815975785255432},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3252394199371338},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26163941621780396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20667552947998047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.135199636220932},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324805","display_name":"Chongqing Municipal Education Commission","ror":"https://ror.org/031nm5713"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W2112796928","https://openalex.org/W2134797427","https://openalex.org/W2335728318","https://openalex.org/W2561238782","https://openalex.org/W2766966408","https://openalex.org/W2945289329","https://openalex.org/W2945528222","https://openalex.org/W2946830201","https://openalex.org/W2951574208","https://openalex.org/W2962785568","https://openalex.org/W2963140444","https://openalex.org/W2963306805","https://openalex.org/W2963373786","https://openalex.org/W2963981733","https://openalex.org/W2963989815","https://openalex.org/W2964121744","https://openalex.org/W2969071643","https://openalex.org/W2970806306","https://openalex.org/W2979359324","https://openalex.org/W2982802130","https://openalex.org/W2984898826","https://openalex.org/W3034368386","https://openalex.org/W3034957837","https://openalex.org/W3118608800","https://openalex.org/W3129336662","https://openalex.org/W4288348717","https://openalex.org/W4288351313","https://openalex.org/W4301206121","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6703116779","https://openalex.org/W6730179637","https://openalex.org/W6745689806","https://openalex.org/W6762640628","https://openalex.org/W6762811270","https://openalex.org/W6762840122","https://openalex.org/W6762887799","https://openalex.org/W6765779288","https://openalex.org/W6766615215","https://openalex.org/W6770540178","https://openalex.org/W6779590286","https://openalex.org/W6781527488"],"related_works":["https://openalex.org/W3216553692","https://openalex.org/W2735450835","https://openalex.org/W3198113463","https://openalex.org/W4285827128","https://openalex.org/W2602382373","https://openalex.org/W2787698406","https://openalex.org/W2963844355","https://openalex.org/W4361251046","https://openalex.org/W4301772239","https://openalex.org/W3095116576"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1],"(KD)":[2],"has":[3,35],"enabled":[4],"remarkable":[5],"progress":[6],"in":[7,31,81,99],"model":[8],"compression":[9],"and":[10,45,73,84,93,116,129,152,181],"knowledge":[11],"transfer.":[12],"However,":[13],"KD":[14,34,62,97,174],"requires":[15],"a":[16,51],"large":[17],"volume":[18],"of":[19,67,77,124],"original":[20],"data":[21],"or":[22],"their":[23],"representation":[24],"statistics":[25],"that":[26,158],"are":[27,48],"not":[28],"usually":[29],"available":[30],"practice.":[32],"Data-free":[33],"recently":[36],"been":[37],"proposed":[38],"to":[39,69,108,171],"resolve":[40],"this":[41,88,100,143],"problem,":[42],"wherein":[43],"teacher":[44],"student":[46],"models":[47],"fed":[49],"by":[50,144],"synthetic":[52],"sample":[53,127],"generator":[54,103],"trained":[55],"from":[56],"the":[57,75,122],"teacher.":[58],"Nonetheless,":[59],"existing":[60],"data-free":[61,96,173],"methods":[63,175],"rely":[64],"on":[65],"fine-tuning":[66],"weights":[68],"balance":[70],"multiple":[71],"losses,":[72],"ignore":[74],"diversity":[76,94,131],"generated":[78],"samples,":[79],"resulting":[80],"limited":[82],"accuracy":[83,162],"robustness.":[85],"To":[86],"overcome":[87],"challenge,":[89],"we":[90],"propose":[91],"robustness":[92,165],"seeking":[95,125],"(RDSKD)":[98],"paper.":[101],"The":[102],"loss":[104,139,147],"function":[105],"is":[106],"crafted":[107],"produce":[109],"samples":[110],"with":[111,134,163],"high":[112,126],"authenticity,":[113],"class":[114,130],"diversity,":[115],"inter-sample":[117],"diversity.":[118],"Without":[119],"real":[120],"data,":[121],"objectives":[123],"authenticity":[128],"often":[132],"conflict":[133],"each":[135],"other,":[136],"causing":[137],"frequent":[138],"fluctuations.":[140],"We":[141],"mitigate":[142],"exponentially":[145],"penalizing":[146],"increments.":[148],"With":[149],"MNIST,":[150],"CIFAR-10,":[151],"SVHN":[153],"datasets,":[154],"our":[155],"experiments":[156],"show":[157],"RDSKD":[159],"achieves":[160],"higher":[161],"more":[164],"over":[166],"different":[167],"hyperparameter":[168],"settings,":[169],"compared":[170],"other":[172],"such":[176],"as":[177],"DAFL,":[178],"MSKD,":[179],"ZSKD,":[180],"DeepInversion.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}