{"id":"https://openalex.org/W4390357613","doi":"https://doi.org/10.1109/tnnls.2023.3342172","title":"Factorization Vision Transformer: Modeling Long-Range Dependency With Local Window Cost","display_name":"Factorization Vision Transformer: Modeling Long-Range Dependency With Local Window Cost","publication_year":2023,"publication_date":"2023-12-28","ids":{"openalex":"https://openalex.org/W4390357613","doi":"https://doi.org/10.1109/tnnls.2023.3342172","pmid":"https://pubmed.ncbi.nlm.nih.gov/38153834"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3342172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3342172","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/A5091025128","display_name":"Haolin Qin","orcid":"https://orcid.org/0000-0001-8569-7430"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haolin Qin","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072984967","display_name":"Daquan Zhou","orcid":"https://orcid.org/0000-0002-4771-1796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daquan Zhou","raw_affiliation_strings":["ByteDance, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019242095","display_name":"Tingfa Xu","orcid":"https://orcid.org/0000-0001-5452-2662"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingfa Xu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China","Beijing Institute of Technology Chongqing Innovation Center, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology Chongqing Innovation Center, Chongqing, China","institution_ids":["https://openalex.org/I50632499","https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000672668","display_name":"Ziyang Bian","orcid":"https://orcid.org/0000-0002-5498-504X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210157275","display_name":"North China Research Institute of Electro-optics","ror":"https://ror.org/04sbk5k46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210157275"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Bian","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China","North China Research Institute of Electro-Optics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"North China Research Institute of Electro-Optics, Beijing, China","institution_ids":["https://openalex.org/I4210157275"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448292","display_name":"Jianan Li","orcid":"https://orcid.org/0000-0002-6936-9485"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianan Li","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091025128"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":1.9241,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88516402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"36","issue":"2","first_page":"3151","last_page":"3164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7482403516769409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.660729706287384},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5192427635192871},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.45970118045806885},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.43165555596351624},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4242344796657562},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4048408269882202},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38864341378211975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3626224398612976},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33011239767074585},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19698166847229004}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7482403516769409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.660729706287384},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5192427635192871},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.45970118045806885},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.43165555596351624},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4242344796657562},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4048408269882202},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38864341378211975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3626224398612976},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33011239767074585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19698166847229004},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3342172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3342172","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:38153834","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38153834","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/G4360217077","display_name":null,"funder_award_id":"62101032","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":105,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1921293667","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2531409750","https://openalex.org/W2553303224","https://openalex.org/W2618530766","https://openalex.org/W2743200750","https://openalex.org/W2797977484","https://openalex.org/W2806070179","https://openalex.org/W2884561390","https://openalex.org/W2896457183","https://openalex.org/W2910628332","https://openalex.org/W2955425717","https://openalex.org/W2963163009","https://openalex.org/W2963691377","https://openalex.org/W2963855133","https://openalex.org/W2996108195","https://openalex.org/W3002391102","https://openalex.org/W3029812440","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3137963805","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3151130473","https://openalex.org/W3163465952","https://openalex.org/W3168101492","https://openalex.org/W3168825659","https://openalex.org/W3172509117","https://openalex.org/W3172801447","https://openalex.org/W3175515048","https://openalex.org/W3190492058","https://openalex.org/W3196660197","https://openalex.org/W3201233590","https://openalex.org/W3213929680","https://openalex.org/W4210576848","https://openalex.org/W4213255732","https://openalex.org/W4214588794","https://openalex.org/W4225463624","https://openalex.org/W4225535860","https://openalex.org/W4225916372","https://openalex.org/W4225922615","https://openalex.org/W4226334005","https://openalex.org/W4226507777","https://openalex.org/W4226512186","https://openalex.org/W4281756776","https://openalex.org/W4283809036","https://openalex.org/W4285483923","https://openalex.org/W4285507497","https://openalex.org/W4286914341","https://openalex.org/W4287122968","https://openalex.org/W4288404646","https://openalex.org/W4292779060","https://openalex.org/W4307772935","https://openalex.org/W4312257978","https://openalex.org/W4312443924","https://openalex.org/W4312599212","https://openalex.org/W4312638656","https://openalex.org/W4312769131","https://openalex.org/W4312805142","https://openalex.org/W4312820606","https://openalex.org/W4312847199","https://openalex.org/W4312856857","https://openalex.org/W4312881242","https://openalex.org/W4312950730","https://openalex.org/W4312977443","https://openalex.org/W4313160444","https://openalex.org/W4315705623","https://openalex.org/W4319663728","https://openalex.org/W4321151009","https://openalex.org/W4381327833","https://openalex.org/W4385346076","https://openalex.org/W4385945212","https://openalex.org/W4386088181","https://openalex.org/W4389977645","https://openalex.org/W6742511895","https://openalex.org/W6755207826","https://openalex.org/W6757555829","https://openalex.org/W6762718338","https://openalex.org/W6771630921","https://openalex.org/W6778883912","https://openalex.org/W6787972765","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6791705549","https://openalex.org/W6794345597","https://openalex.org/W6795140394","https://openalex.org/W6795901243","https://openalex.org/W6796237581","https://openalex.org/W6796931752","https://openalex.org/W6797399245","https://openalex.org/W6801655670","https://openalex.org/W6803680838","https://openalex.org/W6803813760","https://openalex.org/W6804036380","https://openalex.org/W6804133831","https://openalex.org/W6804624231","https://openalex.org/W6811002592","https://openalex.org/W6838981441","https://openalex.org/W6839178539","https://openalex.org/W6839818334","https://openalex.org/W6840156360","https://openalex.org/W6841287799"],"related_works":["https://openalex.org/W2794559785","https://openalex.org/W1754499339","https://openalex.org/W2013873776","https://openalex.org/W2770593030","https://openalex.org/W2950281908","https://openalex.org/W2963117165","https://openalex.org/W1973739845","https://openalex.org/W119752240","https://openalex.org/W2154044472","https://openalex.org/W4210772589"],"abstract_inverted_index":{"Transformers":[0],"have":[1,151],"astounding":[2],"representational":[3],"power":[4],"but":[5],"typically":[6],"consume":[7],"considerable":[8],"computation":[9],"which":[10],"is":[11],"quadratic":[12],"with":[13,130,140],"image":[14,146],"resolution.":[15,148],"The":[16],"prevailing":[17],"Swin":[18],"transformer":[19,128],"reduces":[20],"computational":[21,67,114,142],"costs":[22],"through":[23],"a":[24,63,74,113,131],"local":[25,37,53,86,119],"window":[26,87],"strategy.":[27],"However,":[28],"this":[29],"strategy":[30],"inevitably":[31],"causes":[32],"two":[33],"drawbacks:":[34],"1)":[35],"the":[36,83,96,118,125,185],"window-based":[38],"self-attention":[39,77],"(WSA)":[40],"hinders":[41],"global":[42],"dependency":[43,91],"modeling":[44,92],"capability":[45],"and":[46,69,89,138,158,170,173,197],"2)":[47],"recent":[48],"studies":[49],"point":[50],"out":[51],"that":[52,80],"windows":[54],"impair":[55],"robustness.":[56],"To":[57],"overcome":[58],"these":[59],"challenges,":[60],"we":[61,72,123],"pursue":[62],"preferable":[64],"trade-off":[65],"between":[66],"cost":[68,88,115],"performance.":[70],"Accordingly,":[71],"propose":[73],"novel":[75],"factorization":[76,126],"(FaSA)":[78],"mechanism":[79],"enjoys":[81],"both":[82],"advantages":[84],"of":[85,179],"long-range":[90,106],"capability.":[93],"By":[94],"factorizing":[95],"conventional":[97],"attention":[98],"matrix":[99],"into":[100],"sparse":[101],"subattention":[102],"matrices,":[103],"FaSA":[104],"captures":[105],"dependencies,":[107],"while":[108,201],"aggregating":[109],"mixed-grained":[110],"information":[111],"at":[112,214],"equivalent":[116],"to":[117,168,184],"WSA.":[120],"Leveraging":[121],"FaSA,":[122],"present":[124],"vision":[127],"(FaViT)":[129],"hierarchical":[132],"structure.":[133],"FaViT":[134],"achieves":[135],"high":[136],"performance":[137,155],"robustness,":[139],"linear":[141],"complexity":[143],"concerning":[144],"input":[145],"spatial":[147],"Extensive":[149],"experiments":[150],"shown":[152],"FaViT's":[153],"advanced":[154],"in":[156,177],"classification":[157,193],"downstream":[159],"tasks.":[160],"Furthermore,":[161],"it":[162],"also":[163],"exhibits":[164],"strong":[165],"model":[166,187,203],"robustness":[167,198],"corrupted":[169],"biased":[171],"data":[172],"hence":[174],"demonstrates":[175],"benefits":[176],"favor":[178],"practical":[180],"applications.":[181],"In":[182],"comparison":[183],"baseline":[186],"Swin-T,":[188],"our":[189],"FaViT-B2":[190],"significantly":[191],"improves":[192],"accuracy":[194],"by":[195,199,205],"1%":[196],"7%,":[200],"reducing":[202],"parameters":[204],"14%.":[206],"Our":[207],"code":[208],"will":[209],"soon":[210],"be":[211],"publicly":[212],"available:":[213],"https://github.com/q2479036243/FaViT.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}