{"id":"https://openalex.org/W4226297238","doi":"https://doi.org/10.1109/tpami.2022.3145427","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","display_name":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","publication_year":2022,"publication_date":"2022-01-25","ids":{"openalex":"https://openalex.org/W4226297238","doi":"https://doi.org/10.1109/tpami.2022.3145427","pmid":"https://pubmed.ncbi.nlm.nih.gov/35077359"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3145427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3145427","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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":null,"display_name":"Qibin Hou","orcid":"https://orcid.org/0000-0002-8388-8708"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qibin Hou","raw_affiliation_strings":["School of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihang Jiang","orcid":"https://orcid.org/0000-0002-8096-842X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zihang Jiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Yuan","orcid":"https://orcid.org/0000-0002-2120-5588"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yuan","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ming-Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["School of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuicheng Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Sea AI Lab, Singapore"],"affiliations":[{"raw_affiliation_string":"Sea AI Lab, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Jiashi Feng","orcid":"https://orcid.org/0000-0001-6843-0064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiashi Feng","raw_affiliation_strings":["Sea AI Lab, Singapore"],"affiliations":[{"raw_affiliation_string":"Sea AI Lab, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":15.5177,"has_fulltext":false,"cited_by_count":157,"citation_normalized_percentile":{"value":0.99508703,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"45","issue":"1","first_page":"1328","last_page":"1334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.4977000057697296,"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":0.4977000057697296,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.11829999834299088,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.052400000393390656,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/encode","display_name":"ENCODE","score":0.5699999928474426},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5196999907493591},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5027999877929688},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49149999022483826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.45910000801086426},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.40049999952316284},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.390500009059906},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3725000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6963000297546387},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5699999928474426},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44670000672340393},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.2754000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3145427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3145427","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35077359","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35077359","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2331143823","https://openalex.org/W2549139847","https://openalex.org/W2752782242","https://openalex.org/W2797977484","https://openalex.org/W2963091558","https://openalex.org/W2963855133","https://openalex.org/W2964137095","https://openalex.org/W2981413347","https://openalex.org/W2983446232","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3034429256","https://openalex.org/W3034752215","https://openalex.org/W3035682985","https://openalex.org/W3097065222","https://openalex.org/W3121523901","https://openalex.org/W3138516171","https://openalex.org/W3172509117","https://openalex.org/W3179869055","https://openalex.org/W4214493665","https://openalex.org/W4214634256","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6757817989","https://openalex.org/W6762718338","https://openalex.org/W6764990469","https://openalex.org/W6766978945","https://openalex.org/W6772853553","https://openalex.org/W6775845032","https://openalex.org/W6779602356","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790428460","https://openalex.org/W6790690058","https://openalex.org/W6791705549","https://openalex.org/W6793632291","https://openalex.org/W6795140394","https://openalex.org/W6795252178","https://openalex.org/W6795300077","https://openalex.org/W6796417832","https://openalex.org/W6797153837","https://openalex.org/W6798107787"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,178],"paper,":[2],"we":[3],"present":[4],"Vision":[5,45,63,96,118],"Permutator,":[6],"a":[7,84],"conceptually":[8],"simple":[9],"and":[10,55,69,106,145,191],"data":[11,130],"efficient":[12],"MLP-like":[13,33,171,196],"architecture":[14],"for":[15,173],"visual":[16,174],"recognition.":[17,175],"By":[18],"realizing":[19],"the":[20,23,37,41,49,53,72,110,149,166,185,193],"importance":[21],"of":[22,168,187,195],"positional":[24],"information":[25,39,190],"carried":[26],"by":[27],"2D":[28],"feature":[29,50],"representations,":[30],"unlike":[31],"recent":[32,169],"models":[34],"that":[35,94],"encode":[36],"spatial":[38,43,113,189],"along":[40,52],"flattened":[42],"dimensions,":[44],"Permutator":[46,64,119],"separately":[47],"encodes":[48],"representations":[51],"height":[54],"width":[56],"dimensions":[57],"with":[58],"linear":[59],"projections.":[60],"This":[61],"allows":[62],"to":[65,88,101,157],"capture":[66],"long-range":[67],"dependencies":[68],"meanwhile":[70],"avoid":[71],"attention":[73,116],"building":[74],"process":[75],"in":[76,83],"transformers.":[77,108],"The":[78],"outputs":[79],"are":[80,98],"then":[81],"aggregated":[82],"mutually":[85],"complementing":[86],"manner":[87],"form":[89],"expressive":[90],"representations.":[91],"We":[92,176],"show":[93],"our":[95],"Permutators":[97],"formidable":[99],"competitors":[100],"convolutional":[102],"neural":[103],"networks":[104,172],"(CNNs)":[105],"vision":[107,146],"Without":[109],"dependence":[111],"on":[112,124,183],"convolutions":[114],"or":[115],"mechanisms,":[117],"achieves":[120],"81.5%":[121],"top-1":[122,162],"accuracy":[123],"ImageNet":[125],"without":[126],"extra":[127],"large-scale":[128],"training":[129],"(e.g.,":[131],"ImageNet-22k)":[132],"using":[133],"only":[134],"25M":[135],"learnable":[136],"parameters,":[137],"which":[138],"is":[139,200],"much":[140],"better":[141],"than":[142],"most":[143],"CNNs":[144],"transformers":[147],"under":[148],"same":[150],"model":[151],"size":[152],"constraint.":[153],"When":[154],"scaling":[155],"up":[156],"88M,":[158],"it":[159],"attains":[160],"83.2%":[161],"accuracy,":[163],"greatly":[164],"improving":[165],"performance":[167],"state-of-the-art":[170],"hope":[177],"work":[179],"could":[180],"encourage":[181],"research":[182],"rethinking":[184],"way":[186],"encoding":[188],"facilitate":[192],"development":[194],"models.":[197],"PyTorch/MindSpore/Jittor":[198],"code":[199],"available":[201],"at":[202],"https://github.com/Andrew-Qibin/VisionPermutator.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":15}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2022-05-05T00:00:00"}