{"id":"https://openalex.org/W4389666173","doi":"https://doi.org/10.1109/iros55552.2023.10341519","title":"Superpixel Transformers for Efficient Semantic Segmentation","display_name":"Superpixel Transformers for Efficient Semantic Segmentation","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666173","doi":"https://doi.org/10.1109/iros55552.2023.10341519"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5070302005","display_name":"Alex Zihao Zhu","orcid":"https://orcid.org/0000-0002-2195-014X"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alex Zihao Zhu","raw_affiliation_strings":["Waymo LLC"],"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077206511","display_name":"Jieru Mei","orcid":"https://orcid.org/0000-0002-4710-9463"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieru Mei","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067478162","display_name":"Siyuan Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Qiao","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055394194","display_name":"Hang Yan","orcid":"https://orcid.org/0000-0003-3912-0168"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hang Yan","raw_affiliation_strings":["Waymo LLC"],"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104090814","display_name":"Yukun Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Zhu","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070707237","display_name":"Liang-Chieh Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang-Chieh Chen","raw_affiliation_strings":["ByteDance Research"],"affiliations":[{"raw_affiliation_string":"ByteDance Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012355769","display_name":"Henrik Kretzschmar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henrik Kretzschmar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5070302005"],"corresponding_institution_ids":["https://openalex.org/I4210145145"],"apc_list":null,"apc_paid":null,"fwci":1.3134,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83229797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7651","last_page":"7658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9987999796867371,"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":0.8065453767776489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7838571071624756},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6363176107406616},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6059165596961975},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5239320397377014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5109683275222778},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49076518416404724},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4675033986568451},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4247113764286041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065453767776489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7838571071624756},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6363176107406616},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6059165596961975},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5239320397377014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5109683275222778},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49076518416404724},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4675033986568451},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4247113764286041},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1948751323","https://openalex.org/W2067191022","https://openalex.org/W2112796928","https://openalex.org/W2118246710","https://openalex.org/W2121947440","https://openalex.org/W2150593711","https://openalex.org/W2161236525","https://openalex.org/W2172859194","https://openalex.org/W2194775991","https://openalex.org/W2331143823","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2535516436","https://openalex.org/W2545985378","https://openalex.org/W2560023338","https://openalex.org/W2630837129","https://openalex.org/W2737258237","https://openalex.org/W2883606943","https://openalex.org/W2884822772","https://openalex.org/W2962891704","https://openalex.org/W2963091558","https://openalex.org/W2964309882","https://openalex.org/W3034355852","https://openalex.org/W3096609285","https://openalex.org/W3097065222","https://openalex.org/W3106546328","https://openalex.org/W3109301572","https://openalex.org/W3127751679","https://openalex.org/W3138516171","https://openalex.org/W3168649818","https://openalex.org/W3170841864","https://openalex.org/W3175703004","https://openalex.org/W4214893857","https://openalex.org/W4239510810","https://openalex.org/W4286982960","https://openalex.org/W4312263794","https://openalex.org/W4312443924","https://openalex.org/W4312615272","https://openalex.org/W4312781440","https://openalex.org/W4312815172","https://openalex.org/W4312980231","https://openalex.org/W6631190155","https://openalex.org/W6640295612","https://openalex.org/W6682082992","https://openalex.org/W6739901393","https://openalex.org/W6751795773","https://openalex.org/W6757817989","https://openalex.org/W6763367864","https://openalex.org/W6784094891","https://openalex.org/W6784930956","https://openalex.org/W6797399245","https://openalex.org/W6797784111","https://openalex.org/W6798837711","https://openalex.org/W6809716307"],"related_works":["https://openalex.org/W4285411112","https://openalex.org/W2085033728","https://openalex.org/W2171299904","https://openalex.org/W4390494008","https://openalex.org/W2922442631","https://openalex.org/W2053596378","https://openalex.org/W2168523118","https://openalex.org/W2073639911","https://openalex.org/W2106540031","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Semantic":[0],"segmentation,":[1],"which":[2],"aims":[3],"to":[4,27,43,53,60,78,105,128,131,181,188,202],"classify":[5],"every":[6],"pixel":[7,108,160,171],"in":[8,15,174,198,229,235],"an":[9,87],"image,":[10,91],"is":[11],"a":[12,68,76,96,111,118,143],"key":[13],"task":[14],"machine":[16],"perception,":[17],"with":[18,95,136],"many":[19],"applications":[20],"across":[21],"robotics":[22],"and":[23,92,139,168,217,240],"autonomous":[24],"driving.":[25],"Due":[26],"the":[28,61,83,90,107,129,133,153,159,163,166,169,175,203,209,224,227],"high":[29,62],"dimensionality":[30],"of":[31,65,85,89,120,226,231,237],"this":[32,72,79],"task,":[33],"most":[34],"existing":[35],"approaches":[36],"use":[37],"local":[38,121],"operations,":[39],"such":[40],"as":[41],"convolutions,":[42],"generate":[44],"per-pixel":[45],"features.":[46,172],"However,":[47],"these":[48],"methods":[49],"are":[50],"typically":[51],"unable":[52],"effectively":[54],"leverage":[55],"global":[56,137,210],"context":[57,138],"information":[58],"due":[59,201],"computational":[63],"costs":[64],"operating":[66],"on":[67,215],"dense":[69],"image.":[70],"In":[71,100],"work,":[73],"we":[74,150],"propose":[75],"solution":[77],"issue":[80],"by":[81,208],"leveraging":[82],"idea":[84],"superpixels,":[86],"over-segmentation":[88],"applying":[93],"them":[94],"modern":[97],"transformer":[98],"framework.":[99],"particular,":[101],"our":[102,179,193,221],"model":[103,238],"learns":[104],"decompose":[106],"space":[109,116,161,177],"into":[110,158],"spatially":[112],"low":[113],"dimensional":[114],"superpixel":[115,134,154,176,205],"via":[117],"series":[119],"cross-attentions.":[122],"We":[123],"then":[124,140],"apply":[125],"multi-head":[126],"self-attention":[127,211],"superpixels":[130,167],"enrich":[132],"features":[135,206],"directly":[141,151],"produce":[142],"class":[144,155],"prediction":[145],"for":[146],"each":[147],"superpixel.":[148],"Finally,":[149],"project":[152],"predictions":[156],"back":[157],"using":[162],"associations":[164],"between":[165],"image":[170],"Reasoning":[173],"allows":[178],"method":[180,194,222],"be":[182],"substantially":[183],"more":[184],"computationally":[185],"efficient":[186],"compared":[187],"convolution-based":[189],"decoder":[190],"methods.":[191],"Yet,":[192],"achieves":[195],"state-of-the-art":[196],"performance":[197],"semantic":[199],"segmentation":[200],"rich":[204],"generated":[207],"mechanism.":[212],"Our":[213],"experiments":[214],"Cityscapes":[216],"ADE20K":[218],"demonstrate":[219],"that":[220],"matches":[223],"state":[225],"art":[228],"terms":[230,236],"accuracy,":[232],"while":[233],"outperforming":[234],"parameters":[239],"latency.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}