{"id":"https://openalex.org/W6979244635","doi":null,"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":"2025-03-24","ids":{"openalex":"https://openalex.org/W6979244635"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.18536","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.18536","pdf_url":"https://arxiv.org/pdf/2503.18536","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.18536","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021341559","display_name":"Erjian Guo","orcid":"https://orcid.org/0000-0002-6406-2505","observed_orcids":["https://orcid.org/0000-0002-6406-2505"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Erjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhao, Zhen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Zicheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Tong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Yunyi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yunyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhou, Luping","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Luping","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":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9653000235557556,"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":0.9653000235557556,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.025800000876188278,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0013000000035390258,"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/medical-visual-question-answering","display_name":"medical visual question answering","score":0.9980000257492065},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.9480000138282776},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8450000286102295},{"id":"https://openalex.org/keywords/semantic-noise","display_name":"semantic noise","score":0.3869999945163727},{"id":"https://openalex.org/keywords/conditional-image-generation","display_name":"conditional image generation","score":0.6629999876022339},{"id":"https://openalex.org/keywords/robust-loss-functions","display_name":"robust loss functions","score":0.7360000014305115},{"id":"https://openalex.org/keywords/medical-image-interpretation","display_name":"medical image interpretation","score":0.7720000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688000202178955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6309999823570251},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6054999828338623},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.535099983215332},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3343999981880188},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2503.18536","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.18536","pdf_url":"https://arxiv.org/pdf/2503.18536","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.18536","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.18536","pdf_url":"https://arxiv.org/pdf/2503.18536","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"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],"semantically":[46],"designed":[47],"noise":[48],"types.":[49],"More":[50],"importantly,":[51],"introduce":[53],"DiN":[55],"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]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}