{"id":"https://openalex.org/W4414878628","doi":"https://doi.org/10.1109/iccv51701.2025.00056","title":"Dataset Distillation as Data Compression: A Rate-Utility Perspective","display_name":"Dataset Distillation as Data Compression: A Rate-Utility Perspective","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414878628","doi":"https://doi.org/10.1109/iccv51701.2025.00056"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.17221","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087556686","display_name":"Youneng Bao","orcid":"https://orcid.org/0000-0003-3781-6938"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Youneng Bao","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102881279","display_name":"Yiping Liu","orcid":"https://orcid.org/0000-0002-2554-3269"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiping Liu","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030133705","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0001-7390-7250"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Peng Cheng Laboratory,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657559","display_name":"Yongsheng Liang","orcid":"https://orcid.org/0000-0002-0891-5577"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongsheng Liang","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399466","display_name":"Mu Li","orcid":"https://orcid.org/0000-0002-7327-3304"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mu Li","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020029652","display_name":"Kede Ma","orcid":"https://orcid.org/0000-0001-8608-1128"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kede Ma","raw_affiliation_strings":["City University of Hong Kong,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087556686"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27968095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.8504999876022339,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.8504999876022339,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8442999720573425,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.8373000025749207,"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":0.8051000237464905},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5174000263214111},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.47450000047683716},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.42980000376701355},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.38260000944137573},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.34619998931884766}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.8051000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300999760627747},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5174000263214111},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.25220000743865967},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C154030694","wikidata":"https://www.wikidata.org/wiki/Q1436074","display_name":"Fractionating column","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.17221","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17221","pdf_url":"https://arxiv.org/pdf/2507.17221","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.17221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.17221","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.17221","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17221","pdf_url":"https://arxiv.org/pdf/2507.17221","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4113420822","display_name":null,"funder_award_id":"62472124","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Driven":[0],"by":[1,24,87],"the":[2,93,100,110],"``scale-is-everything''":[3],"paradigm,":[4],"modern":[5],"machine":[6],"learning":[7],"increasingly":[8],"demands":[9],"ever-larger":[10],"datasets":[11],"and":[12,17,103,140,147,169],"models,":[13],"yielding":[14],"prohibitive":[15],"computational":[16],"storage":[18,49,133],"requirements.":[19],"Dataset":[20],"distillation":[21,107,159,167],"mitigates":[22],"this":[23,66],"compressing":[25],"an":[26],"original":[27],"dataset":[28,76],"into":[29],"a":[30,70,117,131],"small":[31],"set":[32],"of":[33,96],"synthetic":[34,54,80],"samples,":[35],"while":[36],"preserving":[37],"its":[38],"full":[39],"utility.":[40],"Yet,":[41],"existing":[42,106],"methods":[43],"either":[44],"maximize":[45],"performance":[46],"under":[47],"fixed":[48],"budgets":[50],"or":[51],"pursue":[52],"suitable":[53],"data":[55],"representations":[56],"for":[57,75,137],"redundancy":[58],"removal,":[59],"without":[60],"jointly":[61],"optimizing":[62],"both":[63],"objectives.":[64],"In":[65],"work,":[67],"we":[68,125],"propose":[69],"joint":[71],"rate-utility":[72,177],"optimization":[73],"method":[74,150],"distillation.":[77],"We":[78,91],"parameterize":[79],"samples":[81],"as":[82,99,109],"optimizable":[83],"latent":[84],"codes":[85],"decoded":[86],"extremely":[88],"lightweight":[89],"networks.":[90],"estimate":[92],"Shannon":[94],"entropy":[95],"quantized":[97],"latents":[98],"rate":[101],"measure":[102],"plug":[104],"any":[105],"loss":[108],"utility":[111],"measure,":[112],"trading":[113],"them":[114],"off":[115],"via":[116],"Lagrange":[118],"multiplier.":[119],"To":[120],"enable":[121],"fair,":[122],"cross-method":[123],"comparisons,":[124],"introduce":[126],"bits":[127],"per":[128],"class":[129],"(bpc),":[130],"precise":[132],"metric":[134],"that":[135],"accounts":[136],"sample,":[138],"label,":[139],"decoder":[141],"parameter":[142],"costs.":[143],"On":[144],"CIFAR-10,":[145],"CIFAR-100,":[146],"ImageNet-128,":[148],"our":[149,172],"achieves":[151],"up":[152],"to":[153],"$170\\times$":[154],"greater":[155],"compression":[156],"than":[157],"standard":[158],"at":[160],"comparable":[161],"accuracy.":[162],"Across":[163],"diverse":[164],"bpc":[165],"budgets,":[166],"losses,":[168],"backbone":[170],"architectures,":[171],"approach":[173],"consistently":[174],"establishes":[175],"better":[176],"trade-offs.":[178]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}