{"id":"https://openalex.org/W4413157603","doi":"https://doi.org/10.1109/cvpr52734.2025.01337","title":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","display_name":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413157603","doi":"https://doi.org/10.1109/cvpr52734.2025.01337"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5021341559","display_name":"Erjian Guo","orcid":"https://orcid.org/0000-0002-6406-2505"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Erjian Guo","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072694516","display_name":"Zhen Zhao","orcid":"https://orcid.org/0000-0002-0796-4078"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhao","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114500326","display_name":"Zicheng Wang","orcid":"https://orcid.org/0000-0002-4286-5120"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zicheng Wang","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461265","display_name":"Tong Chen","orcid":"https://orcid.org/0000-0001-7269-146X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tong Chen","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618416","display_name":"Yunyi Liu","orcid":"https://orcid.org/0000-0002-3065-9872"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yunyi Liu","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100643784","display_name":"Luping Zhou","orcid":"https://orcid.org/0000-0001-8762-2424"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Luping Zhou","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.576,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69067331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"14337","last_page":"14346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7685999870300293,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7685999870300293,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.7623000144958496,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.7177000045776367,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7210458517074585},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4616182744503021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4586735665798187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38387924432754517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210458517074585},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4616182744503021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4586735665798187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38387924432754517},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2807941860","https://openalex.org/W2901466771","https://openalex.org/W2963351448","https://openalex.org/W2979525559","https://openalex.org/W2981873476","https://openalex.org/W3011203675","https://openalex.org/W3011651912","https://openalex.org/W3036586801","https://openalex.org/W3044175177","https://openalex.org/W3138516171","https://openalex.org/W3164670515","https://openalex.org/W3174148569","https://openalex.org/W3200936534","https://openalex.org/W3203255640","https://openalex.org/W4283368635","https://openalex.org/W4283731999","https://openalex.org/W4312933868","https://openalex.org/W4313135270","https://openalex.org/W4315880881","https://openalex.org/W4321195619","https://openalex.org/W4379660316","https://openalex.org/W4379879090","https://openalex.org/W4381598461","https://openalex.org/W4384644330","https://openalex.org/W4386071949","https://openalex.org/W4386566421","https://openalex.org/W4387195417","https://openalex.org/W4390465735","https://openalex.org/W4390872979","https://openalex.org/W4390873054","https://openalex.org/W4390873752","https://openalex.org/W4400856363","https://openalex.org/W4403878433"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Medical":[0],"Visual":[1],"Question":[2],"Answering":[3],"(Med-VQA)":[4],"systems":[5],"benefit":[6],"the":[7,17,33,54,69,140,143],"interpretation":[8],"of":[9,19,142],"medical":[10],"images":[11],"containing":[12],"critical":[13],"clinical":[14],"information.":[15],"However,":[16],"challenge":[18],"noisy":[20,37,64],"labels":[21,38,65],"and":[22,133],"limited":[23],"high-quality":[24],"datasets":[25],"remains":[26],"underexplored.":[27],"To":[28,119],"address":[29,120],"this,":[30],"we":[31,52],"establish":[32],"first":[34],"benchmark":[35],"for":[36,94],"in":[39,66],"Med-VQA":[40],"by":[41,106],"simulating":[42],"human":[43],"mislabeling":[44],"with":[45,90,115,156],"semantically":[46],"designed":[47],"noise":[48,158],"types.":[49],"More":[50],"importantly,":[51],"introduce":[53],"DiN":[55,147],"framework,":[56],"which":[57],"leverages":[58],"a":[59,84,91,129],"diffusion":[60,92],"model":[61,93],"to":[62,137],"handle":[63],"Med-VQA.":[67],"Unlike":[68],"dominant":[70],"classification-based":[71],"VQA":[72],"approaches":[73],"that":[74],"directly":[75],"predict":[76],"answers,":[77],"our":[78,123],"Answer":[79,98],"Diffuser":[80],"(AD)":[81],"module":[82,127],"employs":[83],"coarse-to-fine":[85],"process,":[86],"refining":[87],"answer":[88,113,135],"candidates":[89],"improved":[95],"accuracy.":[96],"The":[97],"Condition":[99],"Generator":[100],"(ACG)":[101],"further":[102,138],"enhances":[103],"this":[104],"process":[105],"generating":[107],"task-specific":[108],"conditional":[109],"information":[110],"via":[111],"integrating":[112],"embeddings":[114],"fused":[116],"image-question":[117],"features.":[118],"label":[121],"noise,":[122],"Noisy":[124],"Label":[125],"Refinement(NLR)":[126],"introduces":[128],"robust":[130],"loss":[131],"function":[132],"dynamic":[134],"adjustment":[136],"boost":[139],"performance":[141],"AD":[144],"module.":[145],"Our":[146],"framework":[148],"consistently":[149],"outperforms":[150],"existing":[151],"methods":[152],"across":[153],"multiple":[154],"benchmarks":[155],"varying":[157],"levels":[159],"<sup":[160],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}