{"id":"https://openalex.org/W4414581237","doi":"https://doi.org/10.48550/arxiv.2505.18399","title":"Taming Diffusion for Dataset Distillation with High Representativeness","display_name":"Taming Diffusion for Dataset Distillation with High Representativeness","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4414581237","doi":"https://doi.org/10.48550/arxiv.2505.18399"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.18399","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18399","pdf_url":"https://arxiv.org/pdf/2505.18399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.18399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001371863","display_name":"Lin Zhao","orcid":"https://orcid.org/0000-0002-9326-3349","observed_orcids":["https://orcid.org/0000-0002-9326-3349"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047861147","display_name":"Yu\u2010Shu Wu","orcid":"https://orcid.org/0000-0002-1031-4500","observed_orcids":["https://orcid.org/0000-0002-1031-4500"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yushu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, Xinru","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xinru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044808270","display_name":"Jianyang Gu","orcid":"https://orcid.org/0000-0002-4060-7427","observed_orcids":["https://orcid.org/0000-0002-4060-7427"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Jianyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990","observed_orcids":["https://orcid.org/0000-0002-3024-7990","https://orcid.org/0009-0009-3924-6466","https://orcid.org/0009-0008-4749-5860"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yanzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101537683","display_name":"Xiaolin Xu","orcid":"https://orcid.org/0000-0002-2840-6665","observed_orcids":["https://orcid.org/0000-0002-2840-6665"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xiaolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024807353","display_name":"Pu Zhao","orcid":"https://orcid.org/0000-0001-8184-6419","observed_orcids":["https://orcid.org/0000-0001-8184-6419"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Pu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043582832","display_name":"Xue Lin","orcid":"https://orcid.org/0000-0001-6210-8883","observed_orcids":["https://orcid.org/0000-0001-6210-8883"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9526000022888184,"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":0.9526000022888184,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01640000008046627,"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":0.012600000016391277,"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/dataset-distillation","display_name":"dataset distillation","score":0.9879999756813049},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.9200000166893005},{"id":"https://openalex.org/keywords/ddim-inversion","display_name":"DDIM inversion","score":0.8370000123977661},{"id":"https://openalex.org/keywords/sampling-plans","display_name":"sampling plans","score":0.6050000190734863},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.6359999775886536}],"concepts":[{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.7329000234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6345999836921692},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5630999803543091},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C51267290","wikidata":"https://www.wikidata.org/wiki/Q5527848","display_name":"Gaussian random field","level":4,"score":0.287200003862381},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.18399","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18399","pdf_url":"https://arxiv.org/pdf/2505.18399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2505.18399","doi":"https://doi.org/10.48550/arxiv.2505.18399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.18399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.18399","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18399","pdf_url":"https://arxiv.org/pdf/2505.18399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"deep":[1],"learning":[2],"models":[3],"demand":[4],"larger":[5],"datasets,":[6],"driving":[7],"the":[8,23,91,94,118,131,135],"need":[9],"for":[10,37,117],"dataset":[11,52,96,158],"distillation":[12,53],"to":[13,22,34,77,89,102,113,128],"create":[14],"compact,":[15],"cost-efficient":[16],"datasets":[17,80],"while":[18],"maintaining":[19],"performance.":[20],"Due":[21],"powerful":[24],"image":[25],"generation":[26],"capability":[27],"of":[28,93],"diffusion,":[29],"it":[30],"has":[31],"been":[32],"introduced":[33],"this":[35,42],"field":[36],"generating":[38],"distilled":[39,79,119],"images.":[40],"In":[41],"paper,":[43],"we":[44,70,85,122],"systematically":[45],"investigate":[46],"issues":[47],"present":[48],"in":[49,157],"current":[50],"diffusion-based":[51,75],"methods,":[54],"including":[55],"inaccurate":[56],"distribution":[57,59],"matching,":[58],"deviation":[60],"with":[61,81,134,154],"random":[62],"noise,":[63],"and":[64,109],"separate":[65],"sampling.":[66],"Building":[67],"on":[68],"this,":[69],"propose":[71,123],"D^3HR,":[72],"a":[73,98,103],"novel":[74],"framework":[76],"generate":[78,114],"high":[82],"representativeness.":[83],"Specifically,":[84],"adopt":[86],"DDIM":[87],"inversion":[88],"map":[90],"latents":[92,116,133],"full":[95],"from":[97],"low-normality":[99],"latent":[100],"domain":[101],"high-normality":[104,136],"Gaussian":[105,137],"domain,":[106],"preserving":[107],"information":[108],"ensuring":[110],"structural":[111],"consistency":[112],"representative":[115,132],"dataset.":[120],"Furthermore,":[121],"an":[124],"efficient":[125],"sampling":[126],"scheme":[127],"better":[129],"align":[130],"distribution.":[138],"Our":[139],"comprehensive":[140],"experiments":[141],"demonstrate":[142],"that":[143],"D^3HR":[144],"can":[145],"achieve":[146],"higher":[147],"accuracy":[148],"across":[149],"different":[150],"model":[151],"architectures":[152],"compared":[153],"state-of-the-art":[155],"baselines":[156],"distillation.":[159],"Source":[160],"code:":[161],"https://github.com/lin-zhao-resoLve/D3HR.":[162]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}