{"id":"https://openalex.org/W3170841864","doi":"https://doi.org/10.1109/cvpr46437.2021.00681","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","display_name":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3170841864","doi":"https://doi.org/10.1109/cvpr46437.2021.00681","mag":"3170841864"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.00681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","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/A5090851249","display_name":"Sixiao Zheng","orcid":"https://orcid.org/0000-0001-8324-1528"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sixiao Zheng","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059453082","display_name":"Jiachen Lu","orcid":"https://orcid.org/0000-0002-9956-3852"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachen Lu","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078109015","display_name":"Hengshuang Zhao","orcid":"https://orcid.org/0000-0001-8277-2706"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028643592","display_name":"Xiatian Zhu","orcid":"https://orcid.org/0000-0002-9284-2955"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiatian Zhu","raw_affiliation_strings":["University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089671069","display_name":"Zekun Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekun Luo","raw_affiliation_strings":["Tencent Youtu Lab"],"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Tencent Youtu Lab"],"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080019095","display_name":"Jianfeng Feng","orcid":"https://orcid.org/0000-0002-9328-5732"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Feng","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014436524","display_name":"Tao Xiang","orcid":"https://orcid.org/0000-0002-2530-1059"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Tao Xiang","raw_affiliation_strings":["Facebook AI","University of Surrey"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042899882","display_name":"Philip H. S. Torr","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip H.S. Torr","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425703","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0003-1031-5420"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5090851249"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":261.6614,"has_fulltext":false,"cited_by_count":3412,"citation_normalized_percentile":{"value":0.99996756,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6877","last_page":"6886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7578591108322144},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7101569771766663},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6959884166717529},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6199625730514526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6173037886619568},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5417613983154297},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4830061197280884},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44817909598350525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42034003138542175},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0633242130279541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578591108322144},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7101569771766663},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6959884166717529},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6199625730514526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6173037886619568},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5417613983154297},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4830061197280884},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44817909598350525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42034003138542175},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0633242130279541},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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":1,"locations":[{"id":"doi:10.1109/cvpr46437.2021.00681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G1203979484","display_name":null,"funder_award_id":"EP/N019474/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W1610060839","https://openalex.org/W1686810756","https://openalex.org/W1745334888","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1923697677","https://openalex.org/W2124592697","https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2507296351","https://openalex.org/W2560023338","https://openalex.org/W2565639579","https://openalex.org/W2598666589","https://openalex.org/W2630837129","https://openalex.org/W2799213142","https://openalex.org/W2886934227","https://openalex.org/W2890782586","https://openalex.org/W2895340641","https://openalex.org/W2896457183","https://openalex.org/W2910628332","https://openalex.org/W2913314773","https://openalex.org/W2925552749","https://openalex.org/W2948080074","https://openalex.org/W2949341804","https://openalex.org/W2950045474","https://openalex.org/W2955058313","https://openalex.org/W2962835968","https://openalex.org/W2963091558","https://openalex.org/W2963108253","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963727650","https://openalex.org/W2963840672","https://openalex.org/W2963858333","https://openalex.org/W2963881378","https://openalex.org/W2964110616","https://openalex.org/W2965391153","https://openalex.org/W2970389371","https://openalex.org/W2970597249","https://openalex.org/W2972321983","https://openalex.org/W2972579614","https://openalex.org/W2981413347","https://openalex.org/W2981689412","https://openalex.org/W2982220924","https://openalex.org/W2983446232","https://openalex.org/W2985459778","https://openalex.org/W2993235622","https://openalex.org/W2997564896","https://openalex.org/W2998108143","https://openalex.org/W3022478135","https://openalex.org/W3023001672","https://openalex.org/W3034345703","https://openalex.org/W3034355852","https://openalex.org/W3034502973","https://openalex.org/W3034885317","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3096678291","https://openalex.org/W3097065222","https://openalex.org/W3107113572","https://openalex.org/W3119586106","https://openalex.org/W3170874841","https://openalex.org/W4251033893","https://openalex.org/W4297733535","https://openalex.org/W4298395628","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6639824700","https://openalex.org/W6640295612","https://openalex.org/W6696085341","https://openalex.org/W6724670942","https://openalex.org/W6739696289","https://openalex.org/W6739901393","https://openalex.org/W6754123467","https://openalex.org/W6754713557","https://openalex.org/W6754879843","https://openalex.org/W6755207826","https://openalex.org/W6758857762","https://openalex.org/W6761021795","https://openalex.org/W6763367864","https://openalex.org/W6763701032","https://openalex.org/W6767153015","https://openalex.org/W6767688279","https://openalex.org/W6772853553","https://openalex.org/W6775170262","https://openalex.org/W6778485988","https://openalex.org/W6781238266","https://openalex.org/W6784333009","https://openalex.org/W6785337528","https://openalex.org/W6785766105","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W1663079876","https://openalex.org/W2069133146","https://openalex.org/W2017545316","https://openalex.org/W2100576949","https://openalex.org/W2159686533","https://openalex.org/W4242339654","https://openalex.org/W2349160795","https://openalex.org/W4286681602","https://openalex.org/W3209312100","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Most":[0],"recent":[1],"semantic":[2,77],"segmentation":[3,78,129],"methods":[4],"adopt":[5],"a":[6,80,87,101,122,127],"fully-convolutional":[7],"network":[8],"(FCN)":[9],"with":[10,27,121],"an":[11,72,98],"encoder-decoder":[12,59],"architecture.":[13],"The":[14],"encoder":[15,117],"progressively":[16],"reduces":[17],"the":[18,38,46,58,106,114,144,162,166,174],"spatial":[19],"resolution":[20,94],"and":[21,93,154],"learns":[22],"more":[23],"abstract/semantic":[24],"visual":[25],"concepts":[26],"larger":[28],"receptive":[29,47],"fields.":[30],"Since":[31],"context":[32,108],"modeling":[33],"is":[34],"critical":[35],"for":[36],"segmentation,":[37],"latest":[39],"efforts":[40],"have":[41],"been":[42],"focused":[43],"on":[44,146,157,173],"increasing":[45],"field,":[48],"through":[49],"either":[50],"dilated/atrous":[51],"convolutions":[52],"or":[53],"inserting":[54],"attention":[55],"modules.":[56],"However,":[57],"based":[60],"FCN":[61],"architecture":[62],"remains":[63],"unchanged.":[64],"In":[65],"this":[66,116],"paper,":[67],"we":[68,85,160],"aim":[69],"to":[70,96,125],"provide":[71,126],"alternative":[73],"perspective":[74],"by":[75],"treating":[76],"as":[79,100],"sequence-to-sequence":[81],"prediction":[82],"task.":[83],"Specifically,":[84],"deploy":[86],"pure":[88],"transformer":[89],"(i.e.,":[90],"without":[91],"convolution":[92],"reduction)":[95],"encode":[97],"image":[99],"sequence":[102],"of":[103,113,143,176],"patches.":[104],"With":[105],"global":[107],"modeled":[109],"in":[110,165],"every":[111],"layer":[112],"transformer,":[115],"can":[118],"be":[119],"combined":[120],"simple":[123],"decoder":[124],"powerful":[128],"model,":[130],"termed":[131],"SEgmentation":[132],"TRansformer":[133],"(SETR).":[134],"Extensive":[135],"experiments":[136],"show":[137],"that":[138],"SETR":[139],"achieves":[140],"new":[141],"state":[142],"art":[145],"ADE20K":[147,169],"(50.28%":[148],"mIoU),":[149],"Pascal":[150],"Context":[151],"(55.83%":[152],"mIoU)":[153],"competitive":[155,168],"results":[156],"Cityscapes.":[158],"Particularly,":[159],"achieve":[161],"first":[163],"position":[164],"highly":[167],"test":[170],"server":[171],"leaderboard":[172],"day":[175],"submission.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":55},{"year":2025,"cited_by_count":652},{"year":2024,"cited_by_count":927},{"year":2023,"cited_by_count":931},{"year":2022,"cited_by_count":614},{"year":2021,"cited_by_count":230},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}