{"id":"https://openalex.org/W7161289842","doi":"https://doi.org/10.1109/tip.2026.3692055","title":"DiCLIP: Diffusion Model Enhances CLIP\u2019s Dense Knowledge for Weakly Supervised Semantic Segmentation","display_name":"DiCLIP: Diffusion Model Enhances CLIP\u2019s Dense Knowledge for Weakly Supervised Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161289842","doi":"https://doi.org/10.1109/tip.2026.3692055","pmid":"https://pubmed.ncbi.nlm.nih.gov/42139125"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3692055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3692055","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/A5136194943","display_name":"Zhiwei Yang","orcid":"https://orcid.org/0000-0002-1910-7815"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Yang","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1910-7815","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136193746","display_name":"Pengfei Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113117","display_name":"Shandong Mental Health Center","ror":"https://ror.org/024x8v141","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210113117"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Song","raw_affiliation_strings":["Shandong Computer Science Center, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0007-2176-9934","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center, Shandong, China","institution_ids":["https://openalex.org/I4210113117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035048021","display_name":"Yucong Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I133868755","display_name":"Shanghai Medical College of Fudan University","ror":"https://ror.org/01zntxs11","country_code":"CN","type":"education","lineage":["https://openalex.org/I133868755","https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucong Meng","raw_affiliation_strings":["Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I133868755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136192303","display_name":"Kexue Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113117","display_name":"Shandong Mental Health Center","ror":"https://ror.org/024x8v141","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210113117"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexue Fu","raw_affiliation_strings":["Shandong Computer Science Center, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center, Shandong, China","institution_ids":["https://openalex.org/I4210113117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136243792","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-2947-8783"},"institutions":[{"id":"https://openalex.org/I133868755","display_name":"Shanghai Medical College of Fudan University","ror":"https://ror.org/01zntxs11","country_code":"CN","type":"education","lineage":["https://openalex.org/I133868755","https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2947-8783","affiliations":[{"raw_affiliation_string":"Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I133868755"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136192268","display_name":"Zhijian Song","orcid":"https://orcid.org/0000-0001-9873-216X"},"institutions":[{"id":"https://openalex.org/I133868755","display_name":"Shanghai Medical College of Fudan University","ror":"https://ror.org/01zntxs11","country_code":"CN","type":"education","lineage":["https://openalex.org/I133868755","https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Song","raw_affiliation_strings":["Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9873-216X","affiliations":[{"raw_affiliation_string":"Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I133868755"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60223553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"5641","last_page":"5656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4316999912261963,"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":0.4316999912261963,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.16249999403953552,"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":0.10100000351667404,"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":0.5703999996185303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5371999740600586},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4952000081539154},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.3490000069141388},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3260999917984009}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7124000191688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6909000277519226},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4952000081539154},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3490000069141388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3260999917984009},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3692055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3692055","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:42139125","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42139125","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/G4202012986","display_name":null,"funder_award_id":"82372097","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"Supervised":[1],"Semantic":[2,92],"Segmentation":[3],"(WSSS)":[4],"with":[5],"image-level":[6],"labels":[7],"typically":[8],"leverages":[9,72],"Class":[10],"Activation":[11],"Maps":[12],"(CAMs)":[13],"to":[14,26,77,118,134,184,197,212],"achieve":[15],"pixel-level":[16],"predictions.":[17],"Recently,":[18],"Contrastive":[19],"Language-Image":[20],"Pre-training":[21],"(CLIP)":[22],"has":[23],"been":[24],"introduced":[25],"generate":[27],"CAMs":[28],"in":[29,123],"WSSS.":[30],"However,":[31],"previous":[32],"WSSS":[33,69],"methods":[34,227],"solely":[35],"adopt":[36],"CLIP's":[37,79,124,153],"vision-language":[38],"paired":[39],"property":[40],"for":[41,98,152],"dense":[42,48,80,99,164],"localization,":[43],"neglecting":[44],"its":[45,157],"inherently":[46],"limited":[47],"knowledge":[49,81,216],"across":[50,82],"both":[51],"visual":[52,108,158,189,215],"and":[53,90,231],"text":[54,171,180],"modalities,":[55],"which":[56],"renders":[57],"CAM":[58,205],"generation":[59,206],"suboptimal.":[60],"In":[61],"this":[62],"work,":[63],"we":[64,192],"propose":[65],"DiCLIP,":[66],"a":[67,149,161,178,199,208,213],"novel":[68,214],"framework":[70],"that":[71,177],"the":[73,104,120,128,141,168,186],"generative":[74,195],"diffusion":[75,142],"model":[76],"enhance":[78],"two":[83],"modalities.":[84],"Specifically,":[85],"Visual":[86],"Correlation":[87],"Enhancement":[88],"(VCE)":[89],"Text":[91],"Augmentation":[93],"(TSA)":[94],"modules":[95],"are":[96],"proposed":[97],"prediction":[100],"enhancement.":[101],"To":[102,166],"improve":[103],"spatial":[105,116],"awareness":[106],"of":[107,170,188],"features,":[109],"our":[110,173],"VCE":[111],"module":[112,133,175],"utilizes":[113],"diffusion's":[114,194],"reliable":[115],"consistency":[117],"mitigate":[119],"over-smoothing":[121],"issue":[122],"attention.":[125],"It":[126],"designs":[127],"Attention":[129],"Clustering":[130],"Refinement":[131],"(ACR)":[132],"reliably":[135],"extract":[136],"diverse":[137],"correlation":[138,145],"maps":[139,146],"from":[140,207],"model.":[143],"The":[144],"act":[147],"as":[148],"diversity":[150],"bias":[151],"self-attention,":[154],"recursively":[155],"pushing":[156],"features":[159],"towards":[160],"more":[162],"discriminative":[163],"distribution.":[165],"augment":[167],"semantics":[169],"embeddings,":[172],"TSA":[174],"argues":[176],"single":[179],"modality":[181],"is":[182,241],"insufficient":[183],"encompass":[185],"variability":[187],"categories.":[190],"Thus,":[191],"leverage":[193],"power":[196],"maintain":[198],"dynamic":[200],"key-value":[201],"cache":[202],"model,":[203],"shifting":[204],"patch-text":[209],"matching":[210],"mechanism":[211],"retrieval":[217],"paradigm.":[218],"With":[219],"these":[220],"enhancements,":[221],"DiCLIP":[222],"not":[223],"only":[224],"outperforms":[225],"state-of-the-art":[226],"on":[228],"PASCAL":[229],"VOC":[230],"MS":[232],"COCO":[233],"but":[234],"also":[235],"significantly":[236],"reduces":[237],"training":[238],"costs.":[239],"Code":[240],"publicly":[242],"available":[243],"at":[244],"https://github.com/zwyang6/DiCLIP.":[245]},"counts_by_year":[],"updated_date":"2026-06-03T06:16:58.514037","created_date":"2026-05-16T00:00:00"}