{"id":"https://openalex.org/W7137832226","doi":"https://doi.org/10.1609/aaai.v40i14.38152","title":"Learning Beyond Vision: Vision-Language Distillation and Edge-Aware Mix Diffusion in Semi-Supervised Semantic Segmentation","display_name":"Learning Beyond Vision: Vision-Language Distillation and Edge-Aware Mix Diffusion in Semi-Supervised Semantic Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137832226","doi":"https://doi.org/10.1609/aaai.v40i14.38152"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38152","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38152","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38152/42114","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38152/42114","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129711509","display_name":"Rui Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Yang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716173","display_name":"Yunfei Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Bai","raw_affiliation_strings":["School of Mechatronic Engineering and Automation, Shanghai University"],"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747879","display_name":"Yuehua Liu","orcid":"https://orcid.org/0000-0002-0312-6763"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehua Liu","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686770","display_name":"Xiaomao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomao Li","raw_affiliation_strings":["School of Mechatronic Engineering and Automation, Shanghai University"],"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129705952","display_name":"Shaorong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaorong Xie","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129711509"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05208333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11676","last_page":"11684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5964999794960022,"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":0.5964999794960022,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16329999268054962,"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":0.054999999701976776,"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":0.6686999797821045},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6593999862670898},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6169000267982483},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46309998631477356},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.382099986076355},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.37229999899864197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37070000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901999950408936},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6686999797821045},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6593999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6473000049591064},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46309998631477356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38152","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38152","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38152/42114","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38152","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38152","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38152/42114","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7148871421813965}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802250152","display_name":null,"funder_award_id":"62421004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4466553724","display_name":null,"funder_award_id":"421004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7174558747","display_name":null,"funder_award_id":"Group","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"},{"id":"https://openalex.org/F4320322271","display_name":"Science Fund for Creative Research Groups","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137832226.pdf","grobid_xml":"https://content.openalex.org/works/W7137832226.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"semi-supervised":[1],"semantic":[2,48,82,120,127],"segmentation":[3,5,196],"(SSSS),":[4],"performance":[6],"is":[7,88,130],"heavily":[8],"constrained":[9],"by":[10],"the":[11,23,28,89,158],"quality":[12,194],"of":[13],"pseudo":[14],"labels.":[15],"However,":[16],"prevalent":[17],"pseudo-label":[18,61,193],"optimization":[19],"approaches":[20],"rely":[21],"on":[22,184],"model\u2019s":[24],"internal":[25],"self-correction.":[26],"When":[27],"model":[29,161],"fails":[30],"to":[31,46,59,72,92,104,118,160],"recognize":[32],"or":[33,49],"adequately":[34],"represent":[35],"certain":[36],"classes,":[37],"this":[38,54,87],"self-enhancement":[39],"mechanism":[40],"amplifies":[41],"initial":[42],"mistakes,":[43],"ultimately":[44],"leading":[45],"poor":[47],"spatial":[50,136],"consistency.":[51,121],"To":[52,84,164],"address":[53],"limitation,":[55],"we":[56,139,168],"propose":[57,140],"ViLaDiff":[58,64],"enhance":[60,105,165],"quality.":[62],"Specifically,":[63],"first":[65,90],"employs":[66],"a":[67,100,170],"prompt-guided":[68],"image":[69],"captioning":[70],"task":[71],"generate":[73],"descriptive":[74],"text":[75],"for":[76],"each":[77],"input":[78],"image,":[79],"providing":[80],"high-level":[81,126],"context.":[83],"our":[85,189],"knowledge,":[86],"attempt":[91],"introduce":[93],"vision-language":[94,101],"modeling":[95,179],"into":[96,157],"SSSS.":[97],"We":[98],"design":[99],"fusion":[102],"module":[103],"feature":[106],"semantics":[107],"and":[108,153,195],"discriminative":[109],"capability.":[110],"It":[111,146],"integrates":[112],"cross-modal":[113],"interactions":[114],"with":[115],"dual-path":[116],"knowledge":[117],"ensure":[119],"Additionally,":[122],"while":[123],"language":[124],"provides":[125],"guidance,":[128],"it":[129],"inherently":[131],"limited":[132],"in":[133],"expressing":[134],"fine-grained":[135],"structures.":[137],"Therefore,":[138],"an":[141],"edge-aware":[142,178],"mixed-noise":[143],"diffusion":[144],"process.":[145],"simulates":[147],"feature-level":[148],"uncertainty":[149],"through":[150],"Gaussian":[151],"perturbations":[152],"introduces":[154],"class-flipping":[155],"noise":[156],"masks":[159],"misclassification":[162],"errors.":[163],"boundary":[166],"refinement,":[167],"apply":[169],"higher":[171],"flipping":[172],"probability":[173],"along":[174],"mask":[175],"edges,":[176],"enabling":[177],"during":[180],"denoising.":[181],"Extensive":[182],"experiments":[183],"public":[185],"benchmarks":[186],"validate":[187],"that":[188],"method":[190],"significantly":[191],"improves":[192],"performance.":[197]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}