{"id":"https://openalex.org/W7128856821","doi":"https://doi.org/10.1109/tpami.2026.3664488","title":"Soft Label Pruning and Quantization for Large-Scale Dataset Distillation","display_name":"Soft Label Pruning and Quantization for Large-Scale Dataset Distillation","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7128856821","doi":"https://doi.org/10.1109/tpami.2026.3664488","pmid":"https://pubmed.ncbi.nlm.nih.gov/41686676"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3664488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664488","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.18135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036496966","display_name":"Lingao Xiao","orcid":"https://orcid.org/0009-0007-1697-1986"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lingao Xiao","raw_affiliation_strings":["CFAR, Agency for Science, Technology and Research, Singapore"],"raw_orcid":"https://orcid.org/0009-0007-1697-1986","affiliations":[{"raw_affiliation_string":"CFAR, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021662942","display_name":"Yang He","orcid":"https://orcid.org/0000-0002-2257-6073"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang He","raw_affiliation_strings":["CFAR, Agency for Science, Technology and Research, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2257-6073","affiliations":[{"raw_affiliation_string":"CFAR, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I115228651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15459609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"7521","last_page":"7533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.6877999901771545,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6877999901771545,"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":0.10209999978542328,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.01600000075995922,"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/quantization","display_name":"Quantization (signal processing)","score":0.7986000180244446},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7103999853134155},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7081999778747559},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6402999758720398},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4740999937057495},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.33570000529289246},{"id":"https://openalex.org/keywords/soft-computing","display_name":"Soft computing","score":0.3294999897480011}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7986000180244446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616000175476074},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7103999853134155},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7081999778747559},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946999788284302},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C140073362","wikidata":"https://www.wikidata.org/wiki/Q738759","display_name":"Soft computing","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C154030694","wikidata":"https://www.wikidata.org/wiki/Q1436074","display_name":"Fractionating column","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2026.3664488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664488","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41686676","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41686676","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2604.18135","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.18135","pdf_url":"https://arxiv.org/pdf/2604.18135","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.18135","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.18135","pdf_url":"https://arxiv.org/pdf/2604.18135","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128856821.pdf","grobid_xml":"https://content.openalex.org/works/W7128856821.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0,82],"dataset":[1,25,160],"distillation":[2,161],"requires":[3,47],"storing":[4],"auxiliary":[5],"soft":[6,126],"labels":[7],"that":[8],"can":[9],"be":[10],"30-40\u00d7":[11],"(ImageNet-1K)":[12],"or":[13],"200\u00d7":[14],"(ImageNet-21K)":[15],"larger":[16],"than":[17],"the":[18,22,150],"condensed":[19],"images,":[20],"undermining":[21],"goal":[23],"of":[24,152],"compression.":[26],"We":[27,85],"identify":[28],"two":[29],"fundamental":[30],"issues":[31],"necessitating":[32],"such":[33],"extensive":[34,48],"labels:":[35],"(1)":[36],"insufficient":[37,52],"image":[38,87],"diversity,":[39,54,99,111],"where":[40,55],"high":[41,68],"within-class":[42],"similarity":[43],"in":[44,58],"synthetic":[45],"images":[46],"augmentation,":[49],"and":[50,79,92,112,133,144,158],"(2)":[51],"supervision":[53,94,98],"limited":[56],"variety":[57],"supervisory":[59],"signals":[60],"during":[61,95],"training":[62],"leads":[63],"to":[64,108,119,142],"performance":[65],"degradation":[66],"at":[67],"compression":[69],"rates.":[70],"To":[71],"address":[72],"these":[73],"challenges,":[74],"we":[75,100],"propose":[76],"Label":[77,102,113],"Pruning":[78,103],"Quantization":[80,114],"for":[81],"Distillation":[83],"(LPQLD).":[84],"enhance":[86,109,120],"diversity":[88],"via":[89],"class-wise":[90],"batching":[91],"BN":[93],"synthesis.":[96],"For":[97],"introduce":[101],"with":[104,115],"Dynamic":[105],"Knowledge":[106],"Reuse":[107],"label-per-augmentation":[110],"Calibrated":[116],"Student-Teacher":[117],"Alignment":[118],"augmentation-per-image":[121],"diversity.":[122],"Our":[123],"approach":[124],"reduces":[125],"label":[127],"storage":[128],"by":[129,140],"78\u00d7":[130],"on":[131,135],"ImageNet-1K":[132],"500\u00d7":[134],"ImageNet-21K":[136],"while":[137],"improving":[138],"accuracy":[139],"up":[141],"7.2%":[143],"2.8%,":[145],"respectively.":[146],"Extensive":[147],"experiments":[148],"validate":[149],"superiority":[151],"LPQLD":[153],"across":[154],"different":[155],"network":[156],"architectures":[157],"other":[159],"methods.":[162]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-14T00:00:00"}