{"id":"https://openalex.org/W3205388591","doi":"https://doi.org/10.1109/icra48506.2021.9561858","title":"YolactEdge: Real-time Instance Segmentation on the Edge","display_name":"YolactEdge: Real-time Instance Segmentation on the Edge","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3205388591","doi":"https://doi.org/10.1109/icra48506.2021.9561858","mag":"3205388591"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100448802","display_name":"Haotian Liu","orcid":"https://orcid.org/0000-0003-2872-4740"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haotian Liu","raw_affiliation_strings":["Amazon Web Services, Inc., University of California, Davis"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc., University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086147608","display_name":"Rafael A. Rivera Soto","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael A. Rivera Soto","raw_affiliation_strings":["Amazon Web Services, Inc., University of California, Davis"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc., University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064761222","display_name":"Fanyi Xiao","orcid":"https://orcid.org/0000-0002-9839-1139"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fanyi Xiao","raw_affiliation_strings":["Amazon Web Services, Inc., University of California, Davis"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc., University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112702739","display_name":"Yong Jae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Jae Lee","raw_affiliation_strings":["Amazon Web Services, Inc., University of California, Davis"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc., University of California, Davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100448802"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":5.1459,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.96603322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9579","last_page":"9585"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9921000003814697,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9869999885559082,"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":0.820838451385498},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7733746767044067},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6486285328865051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.604023277759552},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5642189979553223},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5315178632736206},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4973633587360382},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45961353182792664},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.45525065064430237},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4546109437942505},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44709980487823486},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4452817142009735},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42883360385894775},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34040725231170654},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3399166464805603},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2833144962787628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820838451385498},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7733746767044067},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6486285328865051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.604023277759552},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5642189979553223},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5315178632736206},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4973633587360382},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45961353182792664},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.45525065064430237},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4546109437942505},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44709980487823486},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4452817142009735},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42883360385894775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34040725231170654},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3399166464805603},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2833144962787628},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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":47,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W2119144962","https://openalex.org/W2279098554","https://openalex.org/W2300242332","https://openalex.org/W2552900565","https://openalex.org/W2565639579","https://openalex.org/W2783000019","https://openalex.org/W2787752464","https://openalex.org/W2936599103","https://openalex.org/W2937108468","https://openalex.org/W2944779197","https://openalex.org/W2946948417","https://openalex.org/W2951975689","https://openalex.org/W2955425717","https://openalex.org/W2963150697","https://openalex.org/W2963653352","https://openalex.org/W2963782415","https://openalex.org/W2964203871","https://openalex.org/W2964286567","https://openalex.org/W2964299589","https://openalex.org/W2964444661","https://openalex.org/W2975350394","https://openalex.org/W2978017171","https://openalex.org/W2982083293","https://openalex.org/W2982723417","https://openalex.org/W2982770724","https://openalex.org/W2993182889","https://openalex.org/W3012846999","https://openalex.org/W3021187529","https://openalex.org/W3034428102","https://openalex.org/W3034681942","https://openalex.org/W3035049382","https://openalex.org/W3035709993","https://openalex.org/W3047032303","https://openalex.org/W6638523607","https://openalex.org/W6639102338","https://openalex.org/W6677580257","https://openalex.org/W6695314431","https://openalex.org/W6698200048","https://openalex.org/W6748163181","https://openalex.org/W6762718338","https://openalex.org/W6768287286","https://openalex.org/W6768851824","https://openalex.org/W6770414525","https://openalex.org/W6775059118"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698","https://openalex.org/W2116510815"],"abstract_inverted_index":{"We":[0,115],"propose":[1],"YolactEdge,":[2],"the":[3,55,88],"first":[4],"competitive":[5,109],"instance":[6],"segmentation":[7],"approach":[8],"that":[9,96],"runs":[10,20],"on":[11,26,34,43,87],"small":[12],"edge":[13],"devices":[14],"at":[15,21,132],"real-time":[16,58,105],"speeds.":[17],"Specifically,":[18],"YolactEdge":[19,97],"up":[22,102],"to":[23,54,80,120],"30.8":[24],"FPS":[25,33],"a":[27,40,75,99],"Jetson":[28],"AGX":[29],"Xavier":[30],"(and":[31],"172.7":[32],"an":[35],"RTX":[36],"2080":[37],"Ti)":[38],"with":[39],"ResNet-101":[41],"backbone":[42],"550x550":[44],"resolution":[45],"images.":[46],"To":[47],"achieve":[48],"this,":[49],"we":[50],"make":[51],"two":[52],"improvements":[53],"state-of-the-art":[56],"image-based":[57],"method":[59],"YOLACT":[60],"[1]:":[61],"(1)":[62],"applying":[63],"TensorRT":[64],"optimization":[65],"while":[66,107],"carefully":[67],"trading":[68],"off":[69],"speed":[70,101],"and":[71,73,91,111,125,128],"accuracy,":[72],"(2)":[74],"novel":[76],"feature":[77],"warping":[78],"module":[79],"exploit":[81],"temporal":[82],"redundancy":[83],"in":[84],"videos.":[85],"Experiments":[86],"YouTube":[89],"VIS":[90],"MS":[92],"COCO":[93],"datasets":[94],"demonstrate":[95],"produces":[98],"3-5x":[100],"over":[103],"existing":[104],"methods":[106],"producing":[108],"mask":[110],"box":[112],"detection":[113],"accuracy.":[114],"also":[116],"conduct":[117],"ablation":[118],"studies":[119],"dissect":[121],"our":[122],"design":[123],"choices":[124],"modules.":[126],"Code":[127],"models":[129],"are":[130],"available":[131],"https://github.com/haotian-liu/yolact_edge.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-03T16:38:21.277918","created_date":"2025-10-10T00:00:00"}