{"id":"https://openalex.org/W4393399541","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227428","title":"FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models","display_name":"FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4393399541","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227428"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.20105","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044252882","display_name":"Barbara Toniella Corradini","orcid":"https://orcid.org/0000-0003-3568-5874"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Barbara Toniella Corradini","raw_affiliation_strings":["DIISM University of Siena,Siena,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIISM University of Siena,Siena,Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111151249","display_name":"Mustafa Shukor","orcid":"https://orcid.org/0000-0002-3100-6689"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I51101395","display_name":"Universit\u00e9 Paris 1 Panth\u00e9on-Sorbonne","ror":"https://ror.org/002t25c44","country_code":"FR","type":"education","lineage":["https://openalex.org/I51101395"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mustafa Shukor","raw_affiliation_strings":["CNRS, ISIR Sorbonne Université,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, ISIR Sorbonne Université,Paris,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I51101395"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092189576","display_name":"Paul Couairon","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I51101395","display_name":"Universit\u00e9 Paris 1 Panth\u00e9on-Sorbonne","ror":"https://ror.org/002t25c44","country_code":"FR","type":"education","lineage":["https://openalex.org/I51101395"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paul Couairon","raw_affiliation_strings":["CNRS, ISIR Sorbonne Université,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, ISIR Sorbonne Université,Paris,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I51101395"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065858250","display_name":"Guillaume Couairon","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Couairon","raw_affiliation_strings":["INRIA Sorbonne Université,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Sorbonne Université,Paris,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020560480","display_name":"Franco Scarselli","orcid":"https://orcid.org/0000-0003-1307-0772"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franco Scarselli","raw_affiliation_strings":["DIISM University of Siena,Siena,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIISM University of Siena,Siena,Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108118084","display_name":"Matthieu Cord","orcid":"https://orcid.org/0000-0002-0627-5844"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I220619192","display_name":"Valeo (France)","ror":"https://ror.org/04ryqpf83","country_code":"FR","type":"company","lineage":["https://openalex.org/I220619192"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Cord","raw_affiliation_strings":["CNRS, ISIR Sorbonne Université, Valeo.ai,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, ISIR Sorbonne Université, Valeo.ai,Paris,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I220619192","https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00046028,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9900000095367432,"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/T13629","display_name":"Text Readability and Simplification","score":0.9506000280380249,"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/training","display_name":"Training (meteorology)","score":0.5589407086372375},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5498369932174683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5333777666091919},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5331950187683105},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4338807463645935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3324972987174988},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17292875051498413},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1574307680130005},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08627176284790039},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07430750131607056},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.06213375926017761}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5589407086372375},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5498369932174683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5333777666091919},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5331950187683105},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4338807463645935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3324972987174988},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17292875051498413},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1574307680130005},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08627176284790039},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07430750131607056},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.06213375926017761},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.20105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.20105","pdf_url":"https://arxiv.org/pdf/2403.20105","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.20105","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.20105","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":"pmh:oai:arXiv.org:2403.20105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.20105","pdf_url":"https://arxiv.org/pdf/2403.20105","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393399541.pdf","grobid_xml":"https://content.openalex.org/works/W4393399541.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W4404658388","https://openalex.org/W4406208390","https://openalex.org/W4386076458","https://openalex.org/W4312933868","https://openalex.org/W4390873054","https://openalex.org/W4390873211","https://openalex.org/W4410706541","https://openalex.org/W4312851514","https://openalex.org/W4386057777","https://openalex.org/W3207801859","https://openalex.org/W2948515602","https://openalex.org/W4313555467","https://openalex.org/W4221161877","https://openalex.org/W2799124825","https://openalex.org/W2982106100","https://openalex.org/W4386075561","https://openalex.org/W4312458986","https://openalex.org/W4386075819","https://openalex.org/W4386071604","https://openalex.org/W4386075997","https://openalex.org/W4312420092","https://openalex.org/W2108598243","https://openalex.org/W4312980231","https://openalex.org/W4386065432","https://openalex.org/W4390873752","https://openalex.org/W4412468250","https://openalex.org/W4390872876","https://openalex.org/W4390889782","https://openalex.org/W4403878709","https://openalex.org/W2037227137","https://openalex.org/W1861492603","https://openalex.org/W4386075766","https://openalex.org/W3159481202","https://openalex.org/W3035524453","https://openalex.org/W4312960937","https://openalex.org/W2565639579","https://openalex.org/W3035703639"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Foundation":[0],"models":[1,20,31,58,93],"have":[2],"exhibited":[3],"unprecedented":[4],"capabilities":[5],"across":[6],"various":[7],"domains":[8],"and":[9,84,106,114,135,148,151],"tasks.":[10,50],"Models":[11],"like":[12],"CLIP":[13,130],"bridge":[14],"cross-modal":[15],"representations,":[16],"while":[17],"text-to-image":[18],"diffusion":[19,75,167],"excel":[21],"in":[22],"realistic":[23],"image":[24,65,102],"generation.":[25],"While":[26],"the":[27,69,164],"complexity":[28],"of":[29,166],"these":[30,57,124],"makes":[32],"retraining":[33],"infeasible,":[34],"their":[35],"superior":[36],"performance":[37],"has":[38],"driven":[39],"research":[40],"to":[41,44,55,81,94,117,126],"explore":[42],"how":[43,54],"efficiently":[45],"use":[46],"them":[47],"for":[48,59],"downstream":[49],"Our":[51,86],"work":[52],"explores":[53],"leverage":[56],"dense":[60],"visual":[61,107],"prediction":[62],"tasks,":[63],"specifically":[64],"segmentation.":[66],"To":[67],"avoid":[68],"annotation":[70],"cost":[71],"or":[72],"training":[73],"large":[74],"models,":[76],"we":[77],"constrain":[78],"our":[79],"method":[80],"be":[82],"zero-shot":[83],"training-free.":[85],"pipeline,":[87],"dubbed":[88],"FreeSeg-Diff,":[89],"uses":[90],"open-source":[91],"foundation":[92],"perform":[95],"open-vocabulary":[96],"segmentation":[97,158],"as":[98],"follows:":[99],"(a)":[100],"retrieving":[101],"caption":[103],"(via":[104,109],"BLIP-2)":[105],"features":[108,116,169],"Stable":[110],"Diffusion),":[111],"(b)":[112],"clustering":[113],"binarizing":[115],"form":[118],"class-agnostic":[119],"object":[120],"masks,":[121],"(c)":[122],"mapping":[123],"masks":[125],"textual":[127],"classes":[128],"using":[129],"with":[131],"open":[132],"vocabulary":[133],"support,":[134],"(d)":[136],"refining":[137],"coarse":[138],"masks.":[139],"FreeSeg-Diff":[140],"surpasses":[141],"many":[142],"training-based":[143],"methods":[144],"on":[145],"Pascal":[146],"VOC":[147],"COCO":[149],"datasets":[150],"delivers":[152],"competitive":[153],"results":[154],"against":[155],"recent":[156],"weakly-supervised":[157],"approaches.":[159],"We":[160],"provide":[161],"experiments":[162],"demonstrating":[163],"superiority":[165],"model":[168],"over":[170],"other":[171],"pre-trained":[172],"models.":[173],"Project":[174],"page:":[175],"https://bcorrad.github.io/freesegdiff/.":[176]},"counts_by_year":[],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2024-04-02T00:00:00"}