{"id":"https://openalex.org/W4402817070","doi":"https://doi.org/10.1109/cvpr52733.2024.00341","title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","display_name":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402817070","doi":"https://doi.org/10.1109/cvpr52733.2024.00341"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00341","doi":"https://doi.org/10.1109/cvpr52733.2024.00341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00341","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.12469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101061351","display_name":"Junjiao Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junjiao Tian","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090490013","display_name":"Lavisha Aggarwal","orcid":"https://orcid.org/0009-0006-2280-1302","observed_orcids":["https://orcid.org/0009-0006-2280-1302"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lavisha Aggarwal","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091025064","display_name":"Andrea Cola\u00e7o","orcid":"https://orcid.org/0009-0001-6661-2216","observed_orcids":["https://orcid.org/0009-0001-6661-2216"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Colaco","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088892134","display_name":"Zsolt Kira","orcid":"https://orcid.org/0000-0002-2626-2004","observed_orcids":["https://orcid.org/0000-0002-2626-2004"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zsolt Kira","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023820234","display_name":"Mar Gonz\u00e1lez-Franco","orcid":"https://orcid.org/0000-0001-6165-4495","observed_orcids":["https://orcid.org/0000-0001-6165-4495"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mar Gonzalez-Franco","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.3402,"has_fulltext":true,"cited_by_count":140,"citation_normalized_percentile":{"value":0.99416236,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3554","last_page":"3563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8622999787330627,"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":0.8622999787330627,"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":0.08540000021457672,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01679999940097332,"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/stable-diffusion","display_name":"Stable Diffusion","score":0.671999990940094},{"id":"https://openalex.org/keywords/self-attention-maps","display_name":"self-attention maps","score":0.8199999928474426},{"id":"https://openalex.org/keywords/kullback-leibler-divergence","display_name":"Kullback-Leibler divergence","score":0.9649999737739563},{"id":"https://openalex.org/keywords/segmentation-masks","display_name":"segmentation masks","score":0.6389999985694885},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"image segmentation","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6649951338768005},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5979850888252258},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5528532862663269},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5386379361152649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520694375038147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5100226998329163},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.474619060754776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3846195936203003},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3752185106277466},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.17873013019561768},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14493197202682495},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00341","doi":"https://doi.org/10.1109/cvpr52733.2024.00341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00341","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.12469","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.12469","pdf_url":"https://arxiv.org/pdf/2308.12469","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2308.12469","doi":"https://doi.org/10.48550/arxiv.2308.12469","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.12469","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.12469","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.12469","pdf_url":"https://arxiv.org/pdf/2308.12469","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4641987079","display_name":null,"funder_award_id":"N00014-18-1-2829","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402817070.pdf","grobid_xml":"https://content.openalex.org/works/W4402817070.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2630837129","https://openalex.org/W2953320089","https://openalex.org/W3217026151","https://openalex.org/W4200632170","https://openalex.org/W4221167013","https://openalex.org/W4320166019","https://openalex.org/W4390872669","https://openalex.org/W4390872876","https://openalex.org/W4390874575","https://openalex.org/W7133198812","https://openalex.org/W7133244048"],"related_works":["https://openalex.org/W4405173316","https://openalex.org/W4399444375","https://openalex.org/W4385800640","https://openalex.org/W4391287740","https://openalex.org/W4409367085","https://openalex.org/W4403928478","https://openalex.org/W4415591165","https://openalex.org/W7212061793","https://openalex.org/W4393399541","https://openalex.org/W4402351201"],"abstract_inverted_index":{"Producing":[0],"quality":[1],"segmentation":[2,25,36,115,131],"masks":[3],"for":[4,132],"images":[5],"is":[6,55,162],"a":[7,42,49,95],"fundamental":[8],"problem":[9],"in":[10,48,68,151,156],"computer":[11],"vision.":[12],"Recent":[13],"research":[14],"has":[15,82],"explored":[16],"large-scale":[17],"supervised":[18],"training":[19,33,124],"to":[20,34,63,72,110,128],"enable":[21,35],"zero-":[22],"shot":[23],"transfer":[24],"on":[26,103],"virtually":[27],"any":[28,53,123,133],"image":[29],"style":[30],"and":[31,154],"unsupervised":[32,142],"without":[37,52],"dense":[38],"annotations.":[39],"However,":[40],"constructing":[41],"model":[43,81],"capable":[44],"of":[45,86,166],"segmenting":[46],"anything":[47],"zero-shot":[50,143],"manner":[51],"anno-tations":[54],"still":[56],"challenging.":[57],"In":[58],"this":[59,74],"paper,":[60],"we":[61,93],"propose":[62],"uti-lize":[64],"the":[65,77,140],"self-attention":[66],"layers":[67],"stable":[69,79],"diffusion":[70,80],"models":[71],"achieve":[73],"goal":[75],"because":[76],"pre-trained":[78],"learned":[83],"inherent":[84],"concepts":[85],"objects":[87],"within":[88],"its":[89],"attention":[90,108],"layers.":[91],"Specifically,":[92],"introduce":[94],"simple":[96],"yet":[97],"ef-fective":[98],"iterative":[99],"merging":[100],"process":[101],"based":[102],"measuring":[104],"KL":[105],"divergence":[106],"among":[107],"maps":[109],"merge":[111],"them":[112],"into":[113],"valid":[114],"masks.":[116],"The":[117,159],"proposed":[118],"method":[119,138,146],"does":[120],"not":[121],"re-quire":[122],"or":[125],"language":[126],"dependency":[127],"extract":[129],"qual-ity":[130],"images.":[134],"On":[135],"COCO-Stuff-27,":[136],"our":[137],"surpasses":[139],"prior":[141],"trans-fer":[144],"SOTA":[145],"by":[147],"an":[148],"absolute":[149],"26%":[150],"pixel":[152],"accuracy":[153],"17%":[155],"mean":[157],"IoU.":[158],"project":[160],"page":[161],"at":[163],"https://sites.google.com/view/diffseg/home.11Georgia":[164],"Institute":[165],"Technology":[167]},"counts_by_year":[{"year":2026,"cited_by_count":42},{"year":2025,"cited_by_count":63},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-09-25T00:00:00"}