{"id":"https://openalex.org/W7160533675","doi":"https://doi.org/10.48550/arxiv.2605.04593","title":"DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","display_name":"DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160533675","doi":"https://doi.org/10.48550/arxiv.2605.04593"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.04593","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135627859","display_name":"Zhiwei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075793088","display_name":"Pengfei Song","orcid":"https://orcid.org/0000-0002-9103-6345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035048021","display_name":"Yucong Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Yucong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135541826","display_name":"Kexue Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Kexue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135565810","display_name":"Shuo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135575441","display_name":"Zhijian Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Zhijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6902999877929688,"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":0.6902999877929688,"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":0.1453000009059906,"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":0.030400000512599945,"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/discriminative-model","display_name":"Discriminative model","score":0.6169999837875366},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.593500018119812},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.580299973487854},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4345000088214874},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.42879998683929443},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41690000891685486},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4129999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781499981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.640500009059906},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.593500018119812},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.580299973487854},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.42879998683929443},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.2605.04593","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7525479197502136,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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":"2026-07-01T06:00:48.157686","created_date":"2026-05-08T00:00:00"}