{"id":"https://openalex.org/W7162401269","doi":"https://doi.org/10.48550/arxiv.2605.25022","title":"D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation","display_name":"D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162401269","doi":"https://doi.org/10.48550/arxiv.2605.25022"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25022","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25022","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.25022","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137011618","display_name":"Wenjie Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137035126","display_name":"Haoji Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Haoji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137063009","display_name":"Jiali Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jiali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047922562","display_name":"Xingze Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Xingze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137082846","display_name":"Jing Jillian Wang","orcid":"https://orcid.org/0000-0002-8874-0008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jing","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/T10036","display_name":"Advanced Neural Network Applications","score":0.460999995470047,"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":0.460999995470047,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.34389999508857727,"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":0.04529999941587448,"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/segmentation","display_name":"Segmentation","score":0.6891999840736389},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5166000127792358},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.510699987411499},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48840001225471497},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4869999885559082},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.48260000348091125},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4754999876022339},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47530001401901245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878999710083008},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6891999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6582000255584717},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4754999876022339},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4244999885559082},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.25369998812675476},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25022","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25022","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,"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":"doi:10.48550/arxiv.2605.25022","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25022","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dataset":[0,83],"distillation":[1],"(DD)":[2],"aims":[3],"to":[4,124],"compress":[5],"large-scale":[6],"datasets":[7],"into":[8],"compact":[9],"synthetic":[10],"sets":[11],"while":[12],"preserving":[13],"training":[14,140],"efficacy.":[15],"However,":[16],"existing":[17],"studies":[18],"mainly":[19],"focus":[20],"on":[21,128,195],"image":[22],"classification,":[23],"leaving":[24],"dense":[25,59],"prediction":[26],"tasks":[27],"such":[28],"as":[29],"semantic":[30],"segmentation":[31,43],"largely":[32],"underexplored.":[33],"In":[34,95,113],"this":[35],"work,":[36],"we":[37,78,99,117,145],"identify":[38],"three":[39],"key":[40],"challenges":[41],"for":[42,52,86,157,166],"DD:":[44],"(i)":[45],"long-tailed":[46],"class":[47],"imbalance,":[48],"(ii)":[49],"the":[50,63,129,139,176],"need":[51],"strict":[53],"pixel-wise":[54],"alignment":[55],"between":[56],"images":[57,126],"and":[58,61,160,192,197,207],"labels,":[60],"(iii)":[62],"high":[64],"computational":[65],"cost":[66],"of":[67,142,178,186],"optimizing":[68],"high-resolution":[69],"data":[70],"with":[71,150,199],"complex":[72],"models.":[73],"To":[74,136],"address":[75],"these":[76],"challenges,":[77],"propose":[79],"D3S2,":[80],"a":[81,92,101,106,119,154,161],"Diffusion-guided":[82],"Distillation":[84],"framework":[85],"Semantic":[87],"Segmentation.":[88],"Our":[89],"method":[90,189],"adopts":[91],"two-stage":[93],"design.":[94],"Class-Balanced":[96],"Mask":[97],"Selection,":[98],"construct":[100],"representative":[102],"mask":[103],"set":[104],"via":[105],"greedy":[107],"strategy":[108],"that":[109],"prioritizes":[110],"underrepresented":[111],"classes.":[112],"Diffusion-Guided":[114],"Image":[115],"Synthesis,":[116],"employ":[118],"pretrained":[120],"layout-to-image":[121],"diffusion":[122,148],"model":[123],"generate":[125],"conditioned":[127],"selected":[130],"masks,":[131],"naturally":[132],"ensuring":[133],"spatial":[134],"alignment.":[135],"further":[137],"enhance":[138],"utility":[141],"synthesized":[143],"data,":[144],"introduce":[146],"guided":[147],"sampling":[149],"two":[151],"complementary":[152],"objectives:":[153],"segmentation-consistency":[155],"loss":[156,165],"pixel-level":[158],"alignment,":[159],"class-wise":[162],"feature":[163,169],"matching":[164],"aligning":[167],"per-class":[168],"statistics":[170],"across":[171],"layers.":[172],"Extensive":[173],"experiments":[174],"demonstrate":[175],"superiority":[177],"D3S2.":[179],"Notably,":[180],"at":[181],"an":[182],"extremely":[183],"compression":[184],"rate":[185],"1%,":[187],"our":[188],"achieves":[190],"24.99%":[191],"35.49%":[193],"mIoU":[194],"ADE20K":[196],"COCO-Stuff":[198],"Mask2Former":[200],"(Swin-S),":[201],"outperforming":[202],"random":[203],"selection":[204],"by":[205],"9.34%":[206],"5.70%,":[208],"respectively.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-27T00:00:00"}