{"id":"https://openalex.org/W7167034696","doi":"https://doi.org/10.1109/tip.2026.3707757","title":"DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation Without Information Leakage","display_name":"DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation Without Information Leakage","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7167034696","doi":"https://doi.org/10.1109/tip.2026.3707757","pmid":"https://pubmed.ncbi.nlm.nih.gov/42391076"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3707757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3707757","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129704908","display_name":"Tianchen Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianchen Zeng","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0002-6114-4932","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417855","display_name":"Sai Wang","orcid":"https://orcid.org/0000-0003-3434-1578"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sai Wang","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-6434-9717","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324098","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-1680-8253","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-8458","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8792946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"7222","last_page":"7232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.23469999432563782,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.23469999432563782,"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/T10028","display_name":"Topic Modeling","score":0.21819999814033508,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07199999690055847,"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":0.5777999758720398},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5511000156402588},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5175999999046326},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.5141000151634216},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.34779998660087585},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3467000126838684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5777999758720398},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5175999999046326},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4325999915599823},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.34779998660087585},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3467000126838684},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3707757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3707757","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42391076","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42391076","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1836220556","display_name":null,"funder_award_id":"62225113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2103398101","display_name":null,"funder_award_id":"62372341","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"Expression":[1],"Segmentation":[2],"(RES)":[3],"requires":[4],"models":[5,189],"not":[6],"only":[7],"to":[8,18,64,95,112,125,144,178],"locate":[9],"objects":[10],"specified":[11],"by":[12],"referring":[13],"expressions":[14],"accurately":[15],"but":[16],"also":[17,182],"predict":[19],"complete":[20],"and":[21,45,122,156],"precise":[22,157],"masks.":[23,75],"Existing":[24],"methods":[25,168],"primarily":[26],"focus":[27,71],"on":[28,59,72,169],"complex":[29],"multimodal":[30],"alignment":[31],"for":[32],"object":[33],"grounding,":[34],"often":[35],"neglecting":[36],"mask":[37,179],"quality,":[38,180],"which":[39,91,175],"results":[40],"in":[41,84,149],"incomplete":[42],"foreground":[43],"regions":[44],"imprecise":[46],"boundaries.":[47,158],"To":[48],"address":[49],"these":[50],"challenges,":[51],"we":[52],"propose":[53],"DiffRES,":[54],"a":[55,70],"mask-generating":[56],"framework":[57],"based":[58],"Stable":[60],"Diffusion":[61],"(SD),":[62],"designed":[63],"tackle":[65],"the":[66,79,93,97,108,132,145],"RES":[67,146,188],"problem":[68],"with":[69,120,154],"achieving":[73],"high-quality":[74],"DiffRES":[76,116,163],"effectively":[77],"mitigates":[78],"information":[80,124,133],"leakage":[81,134],"issue":[82],"prevalent":[83],"existing":[85,186],"generative":[86],"dense":[87],"prediction":[88],"diffusion":[89],"models,":[90],"allows":[92],"model":[94],"infer":[96],"target's":[98],"position":[99],"directly":[100,117],"from":[101,142],"noisy":[102],"masks":[103,153],"during":[104],"training":[105],"without":[106],"understanding":[107],"text":[109],"condition,":[110],"leading":[111],"severe":[113],"overfitting.":[114],"Specifically,":[115],"guides":[118],"SD":[119,143],"visual":[121],"linguistic":[123],"generate":[126],"target":[127],"binary":[128,152],"masks,":[129],"fundamentally":[130],"bypassing":[131],"issue.":[135],"This":[136],"approach":[137],"enables":[138],"efficient":[139],"knowledge":[140],"transfer":[141],"task,":[147],"resulting":[148],"precisely":[150],"localized":[151],"sharp":[155],"Extensive":[159],"experiments":[160],"show":[161],"that":[162],"surpasses":[164],"current":[165],"state-of-the-art":[166],"traditional":[167],"boundary":[170],"precision":[171],"(":[172],"$AP_{b}$":[173],")":[174],"is":[176,195],"sensitive":[177],"while":[181],"significantly":[183],"outperforming":[184],"all":[185,191],"SD-based":[187],"across":[190],"metrics.":[192],"Our":[193],"code":[194],"publicly":[196],"available":[197],"at":[198],"https://github.com/charon517-517/DiffRES.":[199]},"counts_by_year":[],"updated_date":"2026-07-09T05:49:46.723101","created_date":"2026-07-03T00:00:00"}