{"id":"https://openalex.org/W4402351201","doi":"https://doi.org/10.1109/access.2024.3456442","title":"MaskDiffusion: Exploiting Pre-Trained Diffusion Models for Semantic Segmentation","display_name":"MaskDiffusion: Exploiting Pre-Trained Diffusion Models for Semantic Segmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402351201","doi":"https://doi.org/10.1109/access.2024.3456442"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3456442","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3456442","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3456442","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081632375","display_name":"Yasufumi Kawano","orcid":"https://orcid.org/0000-0002-2252-1910"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasufumi Kawano","raw_affiliation_strings":["Graduate School of Integrated Design Engineering, Keio University, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2252-1910","affiliations":[{"raw_affiliation_string":"Graduate School of Integrated Design Engineering, Keio University, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070908826","display_name":"Yoshimitsu Aoki","orcid":"https://orcid.org/0000-0001-7361-0027"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimitsu Aoki","raw_affiliation_strings":["Graduate School of Integrated Design Engineering, Keio University, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7361-0027","affiliations":[{"raw_affiliation_string":"Graduate School of Integrated Design Engineering, Keio University, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.6248,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91122235,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"127283","last_page":"127293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9954000115394592,"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":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7837315797805786},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.560589075088501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5202071070671082},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.45337340235710144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3590853810310364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3387294411659241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837315797805786},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.560589075088501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202071070671082},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.45337340235710144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3590853810310364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3387294411659241},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3456442","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3456442","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:49a594e5c6aa4056adaada7095ffdffc","is_oa":true,"landing_page_url":"https://doaj.org/article/49a594e5c6aa4056adaada7095ffdffc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 127283-127293 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3456442","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3456442","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2037227137","https://openalex.org/W2340897893","https://openalex.org/W2561196672","https://openalex.org/W2630837129","https://openalex.org/W2962770929","https://openalex.org/W2990500698","https://openalex.org/W3035574324","https://openalex.org/W3152958377","https://openalex.org/W3159481202","https://openalex.org/W3172288085","https://openalex.org/W3173143063","https://openalex.org/W3182978476","https://openalex.org/W3209532394","https://openalex.org/W4225981824","https://openalex.org/W4226000809","https://openalex.org/W4292432849","https://openalex.org/W4311415873","https://openalex.org/W4312420092","https://openalex.org/W4312933868","https://openalex.org/W4312960937","https://openalex.org/W4365606129","https://openalex.org/W4366208220","https://openalex.org/W4378474398","https://openalex.org/W4383176261","https://openalex.org/W4385245566","https://openalex.org/W4386075561","https://openalex.org/W4386075819","https://openalex.org/W4386076264","https://openalex.org/W4386076708","https://openalex.org/W4390872876","https://openalex.org/W4390874575","https://openalex.org/W4402716476","https://openalex.org/W4402817070","https://openalex.org/W6684578312","https://openalex.org/W6739696289","https://openalex.org/W6751797983","https://openalex.org/W6763578275","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6793615407","https://openalex.org/W6802987763","https://openalex.org/W6804703708","https://openalex.org/W6805335523","https://openalex.org/W6805547681","https://openalex.org/W6809805176","https://openalex.org/W6838639034","https://openalex.org/W6839009181","https://openalex.org/W6842162983","https://openalex.org/W6851607685","https://openalex.org/W6851800889","https://openalex.org/W6852224567","https://openalex.org/W6852690433","https://openalex.org/W6853708643","https://openalex.org/W6856256348","https://openalex.org/W6858607310"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4395685956","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,71,111,128],"is":[2],"essential":[3],"in":[4,35,96,122],"computer":[5],"vision":[6],"for":[7,25,75],"various":[8],"applications,":[9],"yet":[10],"traditional":[11],"approaches":[12],"face":[13],"significant":[14,117],"challenges,":[15],"including":[16,100],"the":[17,31,73,91,108,132],"high":[18],"cost":[19],"of":[20,94,110],"annotation":[21],"and":[22,44,102,119,140,149],"extensive":[23],"training":[24,77],"supervised":[26,36],"learning.":[27],"Additionally,":[28],"due":[29],"to":[30,47,67,81,85,124,138,145],"limited":[32],"predefined":[33],"categories":[34],"learning,":[37],"models":[38],"typically":[39],"struggle":[40],"with":[41],"infrequent":[42],"classes":[43],"are":[45,151],"unable":[46],"predict":[48],"novel":[49],"classes.":[50],"To":[51],"address":[52],"these":[53],"limitations,":[54],"we":[55],"propose":[56],"MaskDiffusion,":[57],"an":[58],"innovative":[59],"approach":[60],"that":[61],"leverages":[62],"pretrained":[63],"frozen":[64],"Stable":[65],"Diffusion":[66],"achieve":[68],"open-vocabulary":[69],"semantic":[70],"without":[72],"need":[74],"additional":[76],"or":[78],"annotation,":[79],"leading":[80],"improved":[82],"performance":[83,93],"compared":[84,137,144],"similar":[86],"methods.":[87],"We":[88],"also":[89],"demonstrate":[90],"superior":[92],"MaskDiffusion":[95,115],"handling":[97],"open":[98],"vocabularies,":[99],"fine-grained":[101],"proper":[103],"noun-based":[104],"categories,":[105],"thus":[106],"expanding":[107],"scope":[109],"applications.":[112],"Overall,":[113],"our":[114],"shows":[116],"qualitative":[118],"quantitative":[120],"improvements":[121],"contrast":[123],"other":[125],"comparable":[126],"unsupervised":[127],"methods,":[129],"i.e.":[130],"on":[131],"Potsdam":[133],"dataset":[134],"(+10.5":[135],"mIoU":[136,143],"GEM)":[139],"COCO-Stuff":[141],"(+14.8":[142],"DiffSeg).":[146],"All":[147],"code":[148],"data":[150],"released":[152],"at":[153],"<uri":[154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Valkyrja3607/MaskDiffusion</uri>.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}