{"id":"https://openalex.org/W4406261177","doi":"https://doi.org/10.1109/bibm62325.2024.10821987","title":"Optimizing Transformer and MLP with Hidden States Perturbation for Medical Visual Question Answering","display_name":"Optimizing Transformer and MLP with Hidden States Perturbation for Medical Visual Question Answering","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406261177","doi":"https://doi.org/10.1109/bibm62325.2024.10821987"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10821987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100349464","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0001-5063-2864"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100830970","display_name":"Xiangdong Su","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Su","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"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":"5515","last_page":"5522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9710999727249146,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9710999727249146,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9508000016212463,"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":0.9028000235557556,"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/question-answering","display_name":"Question answering","score":0.6509053111076355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5686123371124268},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5601701736450195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40660861134529114},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19632360339164734},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14632189273834229},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08342650532722473}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6509053111076355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5686123371124268},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5601701736450195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40660861134529114},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19632360339164734},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14632189273834229},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08342650532722473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10821987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10821987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320241","display_name":"Academy of Medical Sciences","ror":"https://ror.org/00c489v88"},{"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":27,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2901466771","https://openalex.org/W2962858109","https://openalex.org/W2963150162","https://openalex.org/W2963954913","https://openalex.org/W2979525559","https://openalex.org/W2992308087","https://openalex.org/W3094502228","https://openalex.org/W3094950914","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3198570286","https://openalex.org/W3203255640","https://openalex.org/W3203635737","https://openalex.org/W4283075937","https://openalex.org/W4283258232","https://openalex.org/W4284667763","https://openalex.org/W4295917908","https://openalex.org/W4307823382","https://openalex.org/W4313452817","https://openalex.org/W4313527358","https://openalex.org/W6752083267","https://openalex.org/W6760184523","https://openalex.org/W6763165154","https://openalex.org/W6775041699","https://openalex.org/W6779163297","https://openalex.org/W6795140394"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Optimizing":[0],"model":[1,179,227],"performance":[2,61,195],"is":[3],"a":[4,14,31,225],"crucial":[5],"objective":[6],"in":[7,65,113,233],"medical":[8,235],"visual":[9],"question":[10],"answering":[11],"(MedVQA),":[12],"and":[13,58,78,131,151,172,199],"wide":[15],"range":[16],"of":[17,62,110,127,148,160,163,169,196,220],"techniques":[18],"have":[19],"been":[20],"developed":[21],"to":[22,50,106,144,177],"achieve":[23],"this":[24,27],"goal.":[25],"In":[26],"paper,":[28],"we":[29,70],"propose":[30],"novel":[32,226],"technique":[33,229],"called":[34],"network":[35,57],"state":[36,87,189,222],"perturbation,":[37],"which":[38,83,103,120,140,155],"distinguishes":[39],"itself":[40],"from":[41],"existing":[42],"research.":[43],"Our":[44,181],"study":[45],"designs":[46],"four":[47,93],"innovative":[48],"methods":[49,73,95,191],"modify":[51],"the":[52,56,60,66,107,114,124,128,132,145,157,164,186,194,218,234],"hidden":[53,86,108,125,146,158,188,221],"states":[54,109,126,147,159],"within":[55],"improve":[59],"multimodal":[63,231],"models":[64,201,232],"MedVQA":[67,204],"task.":[68],"Specifically,":[69],"evaluate":[71],"these":[72],"on":[74,202],"both":[75],"general":[76],"transformer":[77,198],"multilayer":[79],"perceptron":[80],"(MLP)":[81],"models,":[82],"allow":[84],"for":[85,230],"adjustments":[88],"at":[89],"each":[90],"layer.":[91],"The":[92],"introduced":[94],"are":[96],"as":[97,224],"follows:":[98],"(1)":[99],"Randomly":[100,117,136],"Set":[101],"Zero,":[102],"assigns":[104],"zeros":[105],"different":[111,149,161],"modalities":[112,162],"network;":[115],"(2)":[116],"Replace":[118],"Content,":[119],"performs":[121,173],"interpolation":[122,176],"between":[123],"text":[129],"sequence":[130],"image":[133],"sequence;":[134],"(3)":[135],"Add":[137],"Gaussian":[138,142],"Noise,":[139],"adds":[141],"noise":[143],"modalities;":[150],"(4)":[152],"Pair":[153],"Interpolation,":[154],"interpolates":[156],"current":[165],"sample":[166],"with":[167],"those":[168],"other":[170],"samples":[171],"corresponding":[174],"label":[175],"facilitate":[178],"training.":[180,214],"experimental":[182],"results":[183],"demonstrate":[184],"that":[185],"proposed":[187],"perturbation":[190,223],"significantly":[192],"enhance":[193],"various":[197],"MLP":[200],"multiple":[203],"datasets,":[205],"without":[206],"requiring":[207],"additional":[208],"data":[209],"or":[210],"computational":[211],"resources":[212],"during":[213],"These":[215],"findings":[216],"highlight":[217],"potential":[219],"improvement":[228],"domain.":[236]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}