{"id":"https://openalex.org/W4415537027","doi":"https://doi.org/10.1145/3746027.3755076","title":"Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation","display_name":"Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537027","doi":"https://doi.org/10.1145/3746027.3755076"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755076","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5027300965","display_name":"Fenghe Tang","orcid":"https://orcid.org/0009-0009-6193-4855"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenghe Tang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0009-6193-4855","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064790701","display_name":"Bingkun Nian","orcid":"https://orcid.org/0000-0001-8263-2383"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingkun Nian","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8263-2383","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748510","display_name":"Jianrui Ding","orcid":"https://orcid.org/0000-0002-3408-9301"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianrui Ding","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-3408-9301","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109538291","display_name":"Wenxin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Ma","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-0967-2344","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097928189","display_name":"Quan Quan","orcid":"https://orcid.org/0000-0001-7787-509X"},"institutions":[{"id":"https://openalex.org/I4210122501","display_name":"Hunan Xiangdian Test Research Institute (China)","ror":"https://ror.org/0391pty66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210122501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Quan","raw_affiliation_strings":["State Grid Hunan Electric Power Corporation Limited Research Institute, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-7787-509X","affiliations":[{"raw_affiliation_string":"State Grid Hunan Electric Power Corporation Limited Research Institute, Changsha, Hunan, China","institution_ids":["https://openalex.org/I4210122501"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113355125","display_name":"Chengqi Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqi Dong","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0001-7273-3911","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404947","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0003-4801-7162"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4801-7162","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763568","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0001-6351-9019"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6351-9019","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028465673","display_name":"S. Kevin Zhou","orcid":"https://orcid.org/0000-0002-6881-4444"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"S. Kevin Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-6881-4444","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3408","last_page":"3417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5619000196456909},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.48739999532699585},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4803999960422516},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4458000063896179},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4092999994754791},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.38269999623298645},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.33730000257492065},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.33730000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864999771118164},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5619000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49880000948905945},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4458000063896179},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3815000057220459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.28439998626708984},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755076","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2560328367","https://openalex.org/W2778618465","https://openalex.org/W2963163009","https://openalex.org/W3197957534","https://openalex.org/W4212875960","https://openalex.org/W4312428231","https://openalex.org/W4385453053","https://openalex.org/W4403152483"],"related_works":[],"abstract_inverted_index":{"In":[0],"clinical":[1],"practice,":[2],"medical":[3,26,38,44,75,137,206],"image":[4,76,207],"analysis":[5],"often":[6],"requires":[7],"efficient":[8,113,198],"execution":[9],"on":[10,25,188],"resource-constrained":[11],"mobile":[12,16,64,205],"devices.":[13],"However,":[14],"existing":[15],"models-primarily":[17],"optimized":[18],"for":[19,74,148,160,204],"natural":[20,36],"images-tend":[21],"to":[22,29],"perform":[23],"poorly":[24],"tasks":[27],"due":[28],"the":[30,81,128],"significant":[31],"information":[32,115,130],"density":[33,131],"gap":[34],"between":[35],"and":[37,55,109,132,144,151,178,201],"domains.":[39],"Combining":[40],"computational":[41,166],"efficiency":[42],"with":[43,95,156],"imaging-specific":[45],"architectural":[46],"advantages":[47],"remains":[48],"a":[49,63,86,91,119,142,153],"challenge":[50],"when":[51],"developing":[52],"lightweight,":[53],"universal,":[54],"high-performing":[56],"networks.":[57],"To":[58,111],"address":[59],"this,":[60],"we":[61,79,117,140],"propose":[62],"model":[65],"called":[66],"Mobile":[67],"U-shaped":[68],"Vision":[69],"Transformer":[70],"(Mobile":[71],"U-ViT)":[72],"tailored":[73],"segmentation.":[77],"Specifically,":[78],"employ":[80,152],"newly":[82],"proposed":[83],"ConvUtr":[84],"as":[85,196],"hierarchical":[87],"patch":[88],"embedding,":[89],"featuring":[90],"parameter-efficient":[92],"large-kernel":[93],"CNN":[94],"inverted":[96],"bottleneck":[97,147],"fusion.":[98],"This":[99],"design":[100],"exhibits":[101],"transformer-like":[102],"representation":[103],"learning":[104],"capacity":[105],"while":[106],"being":[107],"lighter":[108],"faster.":[110],"enable":[112],"local-global":[114],"exchange,":[116],"introduce":[118],"novel":[120],"Large-kernel":[121],"Local-Global-Local":[122],"(LKLGL)":[123],"block":[124],"that":[125],"effectively":[126],"balances":[127],"low":[129],"high-level":[133],"semantic":[134],"discrepancy":[135],"of":[136],"images.":[138],"Finally,":[139],"incorporate":[141],"shallow":[143],"lightweight":[145],"transformer":[146],"long-range":[149],"modeling":[150],"cascaded":[154],"decoder":[155],"downsampled":[157],"skip":[158],"connections":[159],"dense":[161],"prediction.":[162],"Despite":[163],"its":[164],"reduced":[165],"demands,":[167],"our":[168],"medical-optimized":[169],"architecture":[170],"achieves":[171],"state-of-the-art":[172],"performance":[173],"across":[174],"eight":[175],"public":[176],"2D":[177],"3D":[179],"datasets":[180],"covering":[181],"diverse":[182],"imaging":[183],"modalities,":[184],"including":[185],"zero-shot":[186],"testing":[187],"four":[189],"unseen":[190],"datasets.":[191],"These":[192],"results":[193],"establish":[194],"it":[195],"an":[197],"yet":[199],"powerful":[200],"generalization":[202],"solution":[203],"analysis.":[208],"Code":[209],"is":[210],"available":[211],"at:":[212],"https://github.com/FengheTan9/Mobile-U-ViT.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":12}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-25T00:00:00"}