{"id":"https://openalex.org/W7133196671","doi":"https://doi.org/10.52202/068431-0084","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","display_name":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7133196671","doi":"https://doi.org/10.52202/068431-0084"},"language":"en","primary_location":{"id":"doi:10.52202/068431-0084","doi":"https://doi.org/10.52202/068431-0084","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-0084","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.08575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101135616","display_name":"Meng-Hao Guo","orcid":"https://orcid.org/0000-0002-4128-4594","observed_orcids":["https://orcid.org/0000-0002-4128-4594"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng-Hao Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065936389","display_name":"Cheng-Ze Lu","orcid":"https://orcid.org/0000-0002-8225-6311","observed_orcids":["https://orcid.org/0000-0002-8225-6311"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-Ze Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040392623","display_name":"Qibin Hou","orcid":"https://orcid.org/0000-0002-8388-8708","observed_orcids":["https://orcid.org/0000-0002-8388-8708"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qibin Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090961406","display_name":"Zhengning Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengning Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758","observed_orcids":["https://orcid.org/0000-0001-5550-8758"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125570583","display_name":"Shi-Min Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi-Min Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":63.0484,"has_fulltext":true,"cited_by_count":1021,"citation_normalized_percentile":{"value":0.99895728,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1140","last_page":"1156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0017000000225380063,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.00039999998989515007,"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/semantic-segmentation","display_name":"semantic segmentation","score":0.9010000228881836},{"id":"https://openalex.org/keywords/convolutional-attention","display_name":"convolutional attention","score":0.9419999718666077},{"id":"https://openalex.org/keywords/efficient-neural-network-architecture","display_name":"efficient neural network architecture","score":0.5910000205039978},{"id":"https://openalex.org/keywords/lightweight-segmentation-network","display_name":"lightweight segmentation model","score":0.6800000071525574},{"id":"https://openalex.org/keywords/pascal-voc-2012","display_name":"Pascal VOC 2012","score":0.8370000123977661},{"id":"https://openalex.org/keywords/pascal-context","display_name":"Pascal Context","score":0.781000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.675599992275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5924000144004822},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3573000133037567},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/068431-0084","doi":"https://doi.org/10.52202/068431-0084","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-0084","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.08575","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.08575","pdf_url":"https://arxiv.org/pdf/2209.08575","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.08575","doi":"https://doi.org/10.48550/arxiv.2209.08575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.08575","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.08575","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.08575","pdf_url":"https://arxiv.org/pdf/2209.08575","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133196671.pdf","grobid_xml":"https://content.openalex.org/works/W7133196671.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1923697677","https://openalex.org/W2286929393","https://openalex.org/W2630837129","https://openalex.org/W2908510526","https://openalex.org/W3016719260","https://openalex.org/W3155050726","https://openalex.org/W3165745140","https://openalex.org/W3175515048","https://openalex.org/W3212386989","https://openalex.org/W4302275239","https://openalex.org/W4312790276","https://openalex.org/W4385346076","https://openalex.org/W6931259419"],"related_works":["https://openalex.org/W4408973610","https://openalex.org/W3034681889","https://openalex.org/W2804488433","https://openalex.org/W3194489714","https://openalex.org/W4310884128","https://openalex.org/W3048265489","https://openalex.org/W3118611141","https://openalex.org/W7155030880","https://openalex.org/W4407091684","https://openalex.org/W3161838454"],"abstract_inverted_index":{"We":[0],"present":[1],"SegNeXt,":[2],"a":[3,40,83],"simple":[4],"convolutional":[5,37,85,91],"network":[6,87],"architecture":[7],"for":[8],"semantic":[9,19],"segmentation.":[10],"Recent":[11],"transformer-based":[12],"models":[13],"have":[14],"dominated":[15],"the":[16,23,51,58,72,101,131,153,157,161],"field":[17],"of":[18,25,75,103,141],"segmentation":[20,63,76],"due":[21],"to":[22,46,71,81,152],"efficiency":[24],"self-attention":[26,52],"in":[27,54],"encoding":[28],"spatial":[29],"information.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,65],"show":[35],"that":[36,88],"attention":[38,86],"is":[39,167],"more":[41],"efficient":[42],"and":[43,95,118,126,172],"effective":[44],"way":[45],"encode":[47],"contextual":[48],"information":[49],"than":[50],"mechanism":[53],"transformers.":[55],"By":[56],"re-examining":[57],"characteristics":[59],"owned":[60],"by":[61],"successful":[62],"models,":[64],"discover":[66],"several":[67],"key":[68],"components":[69],"leading":[70],"performance":[73,102],"improvement":[74],"models.":[77],"This":[78],"motivates":[79],"us":[80],"design":[82],"novel":[84],"uses":[89],"cheap":[90],"operations.":[92],"Without":[93],"bells":[94],"whistles,":[96],"our":[97],"SegNeXt":[98,121,145],"significantly":[99],"improves":[100],"previous":[104],"state-of-the-art":[105,154],"methods":[106,155],"on":[107,130,156],"popular":[108],"benchmarks,":[109],"including":[110],"ADE20K,":[111],"Cityscapes,":[112],"COCO-Stuff,":[113],"Pascal":[114,116,132],"VOC,":[115],"Context,":[117],"iSAID.":[119],"Notably,":[120],"outperforms":[122],"EfficientNet-L2":[123],"w/":[124],"NAS-FPN":[125],"achieves":[127,146],"90.6%":[128],"mIoU":[129,149],"VOC":[133],"2012":[134],"test":[135],"leaderboard":[136],"using":[137],"only":[138],"1/10":[139],"parameters":[140],"it.":[142],"On":[143],"average,":[144],"about":[147],"2.0%":[148],"improvements":[150],"compared":[151],"ADE20K":[158],"datasets":[159],"with":[160],"same":[162],"or":[163],"fewer":[164],"computations.":[165],"Code":[166],"available":[168],"at":[169],"https://github.com/uyzhang/JSeg":[170],"(Jittor)":[171],"https://github.com/Visual-Attention-Network/SegNeXt":[173],"(Pytorch).":[174]},"counts_by_year":[{"year":2026,"cited_by_count":255},{"year":2025,"cited_by_count":295},{"year":2024,"cited_by_count":333},{"year":2023,"cited_by_count":133},{"year":2022,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-03-03T00:00:00"}