{"id":"https://openalex.org/W4390075009","doi":"https://doi.org/10.1109/tnnls.2023.3342141","title":"ViT-MVT: A Unified Vision Transformer Network for Multiple Vision Tasks","display_name":"ViT-MVT: A Unified Vision Transformer Network for Multiple Vision Tasks","publication_year":2023,"publication_date":"2023-12-21","ids":{"openalex":"https://openalex.org/W4390075009","doi":"https://doi.org/10.1109/tnnls.2023.3342141","pmid":"https://pubmed.ncbi.nlm.nih.gov/38127606"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3342141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3342141","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5050985620","display_name":"Tao Xie","orcid":"https://orcid.org/0000-0002-4179-2898"},"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"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Xie","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","SenseTime Group Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"SenseTime Group Inc, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062787869","display_name":"Kun Dai","orcid":"https://orcid.org/0000-0002-6714-3394"},"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":"Kun Dai","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044025518","display_name":"Zhiqiang Jiang","orcid":"https://orcid.org/0009-0000-3890-7220"},"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":"Zhiqiang Jiang","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639939","display_name":"Ruifeng Li","orcid":"https://orcid.org/0000-0002-1383-7745"},"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":"Ruifeng Li","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039198461","display_name":"Shouren Mao","orcid":"https://orcid.org/0000-0001-8442-8845"},"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":"Shouren Mao","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693413","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-5615-0847"},"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":"Ke Wang","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045865179","display_name":"Lijun Zhao","orcid":"https://orcid.org/0000-0002-9108-8276"},"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":"Lijun Zhao","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5050985620"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210128910"],"apc_list":null,"apc_paid":null,"fwci":3.6294,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94462899,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"36","issue":"2","first_page":"3027","last_page":"3041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8103635311126709},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5629866123199463},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47697576880455017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4588608741760254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3905371427536011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103635311126709},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5629866123199463},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47697576880455017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4588608741760254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3905371427536011},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3342141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3342141","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38127606","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38127606","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6217443170","display_name":null,"funder_award_id":"62176072","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6488581878","display_name":null,"funder_award_id":"62073101","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2549139847","https://openalex.org/W2737258237","https://openalex.org/W2884822772","https://openalex.org/W2946547492","https://openalex.org/W2960010704","https://openalex.org/W2962864421","https://openalex.org/W2963150697","https://openalex.org/W2963402313","https://openalex.org/W2963430933","https://openalex.org/W2963498646","https://openalex.org/W2964081807","https://openalex.org/W2965658867","https://openalex.org/W2998310140","https://openalex.org/W3034727271","https://openalex.org/W3096533519","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3143320354","https://openalex.org/W3170841864","https://openalex.org/W3171125843","https://openalex.org/W3176153963","https://openalex.org/W3180150746","https://openalex.org/W3198817488","https://openalex.org/W3204801262","https://openalex.org/W4214669216","https://openalex.org/W4226512186","https://openalex.org/W4296437452","https://openalex.org/W4312446817","https://openalex.org/W4312836739","https://openalex.org/W4312881242","https://openalex.org/W4312960790","https://openalex.org/W4313047844","https://openalex.org/W4313166619","https://openalex.org/W4319452844","https://openalex.org/W4323897056","https://openalex.org/W4367663369","https://openalex.org/W4385245566","https://openalex.org/W4386071964","https://openalex.org/W4386075796","https://openalex.org/W4386076221","https://openalex.org/W6638319203","https://openalex.org/W6690026940","https://openalex.org/W6752515464","https://openalex.org/W6761472960","https://openalex.org/W6763233178","https://openalex.org/W6766225098","https://openalex.org/W6770205404","https://openalex.org/W6788135285","https://openalex.org/W6790273475","https://openalex.org/W6790690058","https://openalex.org/W6798016242","https://openalex.org/W6802094109","https://openalex.org/W6849846199"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,66,118,143,189],"seek":[4],"to":[5,75,112,133,168,180,196,266],"learn":[6,181],"multiple":[7,115,236],"mainstream":[8],"vision":[9,35],"tasks":[10,48,203,216,238,268],"concurrently":[11],"using":[12],"a":[13,29,40,50,71,88,120,127,145,173,191],"unified":[14],"network,":[15],"which":[16,209],"is":[17,159,259,278],"storage-efficient":[18],"as":[19,85,87],"numerous":[20,46],"networks":[21,222],"with":[22,70,109,126,220],"task-shared":[23,170],"parameters":[24,171,179],"can":[25],"be":[26],"implanted":[27],"into":[28,49],"single":[30],"consolidated":[31],"network.":[32],"Our":[33],"framework,":[34],"transformer":[36,157],"(ViT)-MVT,":[37],"built":[38],"on":[39],"plain":[41],"and":[42,53,82,93,177],"nonhierarchical":[43],"ViT,":[44],"incorporates":[45],"visual":[47,215,237],"modest":[51],"supernet":[52],"optimizes":[54],"them":[55],"jointly":[56],"across":[57],"various":[58,135],"dataset":[59],"domains.":[60],"For":[61],"the":[62,68,80,103,110,156,211],"design":[63,144],"of":[64,130,155,175,261],"ViT-MVT,":[65],"augment":[67],"ViT":[69],"multihead":[72],"self-attention":[73],"(MHSE)":[74],"offer":[76,134],"complementary":[77],"cues":[78],"in":[79,102],"channel":[81],"spatial":[83],"dimension,":[84],"well":[86],"local":[89,104],"perception":[90],"unit":[91],"(LPU)":[92],"locality":[94],"feed-forward":[95],"network":[96],"(locality":[97],"FFN)":[98],"for":[99,138,163,172,201,224,235,273],"information":[100],"exchange":[101],"region,":[105],"thus":[106],"endowing":[107],"ViT-MVT":[108,167,231,254,258],"ability":[111],"effectively":[113],"optimize":[114],"tasks.":[116,140,275],"Besides,":[117],"construct":[119],"search":[121,194],"space":[122],"comprising":[123],"potential":[124],"architectures":[125],"broad":[128],"spectrum":[129],"model":[131,206],"sizes":[132],"optimum":[136],"candidates":[137],"diverse":[139],"After":[141],"that,":[142],"layer-adaptive":[146],"sharing":[147],"technique":[148],"that":[149,185,214,230,252],"automatically":[150],"determines":[151],"whether":[152],"each":[153],"layer":[154],"block":[158],"shared":[160],"or":[161],"not":[162],"all":[164,202],"tasks,":[165],"enabling":[166],"obtain":[169],"reduction":[174],"storage":[176,247],"task-specific":[178],"task-related":[182],"features":[183],"such":[184],"boosting":[186],"performance.":[187],"Finally,":[188],"introduce":[190],"joint-task":[192],"evolutionary":[193],"algorithm":[195],"discover":[197],"an":[198],"optimal":[199],"backbone":[200,221],"under":[204],"total":[205,246],"size":[207],"constraint,":[208],"challenges":[210],"conventional":[212],"wisdom":[213],"are":[217],"typically":[218],"supplied":[219],"developed":[223],"image":[225],"classification.":[226],"Extensive":[227],"experiments":[228],"reveal":[229],"delivers":[232],"exceptional":[233],"performances":[234,272],"over":[239],"state-of-the-art":[240],"methods":[241],"while":[242,269],"necessitating":[243],"considerably":[244],"fewer":[245],"costs.":[248],"We":[249],"further":[250],"demonstrate":[251],"once":[253],"has":[255],"been":[256],"trained,":[257],"capable":[260],"incremental":[262],"learning":[263],"when":[264],"generalized":[265],"new":[267],"retaining":[270],"identical":[271],"trained":[274],"The":[276],"code":[277],"available":[279],"at":[280],"https://github.com/XT-1997/vitmvt.":[281]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}