{"id":"https://openalex.org/W4200198655","doi":"https://doi.org/10.1109/tip.2021.3135717","title":"SODAR: Exploring Locally Aggregated Learning of Mask Representations for Instance Segmentation","display_name":"SODAR: Exploring Locally Aggregated Learning of Mask Representations for Instance Segmentation","publication_year":2021,"publication_date":"2021-12-22","ids":{"openalex":"https://openalex.org/W4200198655","doi":"https://doi.org/10.1109/tip.2021.3135717","pmid":"https://pubmed.ncbi.nlm.nih.gov/34936556"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3135717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3135717","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","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":"https://openalex.org/A5100453495","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-2480-878X"},"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":true,"raw_author_name":"Tao Wang","raw_affiliation_strings":["NUS Graduate School of Integrative Sciences and Engineering and the Institute of Data Science, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"NUS Graduate School of Integrative Sciences and Engineering and the Institute of Data Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014937540","display_name":"Jun Hao Liew","orcid":"https://orcid.org/0000-0002-7538-6759"},"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":"Jun Hao Liew","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":"https://openalex.org/A5101842458","display_name":"Yu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029978692","display_name":"Yunpeng Chen","orcid":"https://orcid.org/0000-0002-9830-8980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunpeng Chen","raw_affiliation_strings":["YITU Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"YITU Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668696","display_name":"Jiashi Feng","orcid":"https://orcid.org/0000-0001-6843-0064"},"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":"Jiashi Feng","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100453495"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0969,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42682808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"31","issue":null,"first_page":"839","last_page":"851"},"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":0.9966999888420105,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9955999851226807,"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":0.7146254777908325},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6413896679878235},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.635496199131012},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5772877931594849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5699449777603149},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5621288418769836},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4979124069213867},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4820047914981842},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4449571371078491},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43806153535842896},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.43739938735961914},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2018590271472931},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1736665666103363},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09814125299453735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146254777908325},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6413896679878235},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.635496199131012},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5772877931594849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699449777603149},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5621288418769836},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4979124069213867},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4820047914981842},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4449571371078491},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43806153535842896},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.43739938735961914},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2018590271472931},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1736665666103363},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09814125299453735},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2021.3135717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3135717","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","raw_type":"journal-article"},{"id":"pmid:34936556","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34936556","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7099999785423279,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1507506748","https://openalex.org/W1538131130","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1932624639","https://openalex.org/W2031489346","https://openalex.org/W2101926813","https://openalex.org/W2116341502","https://openalex.org/W2194775991","https://openalex.org/W2216125271","https://openalex.org/W2340897893","https://openalex.org/W2555182955","https://openalex.org/W2560609797","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2736596806","https://openalex.org/W2744404335","https://openalex.org/W2746726611","https://openalex.org/W2777795072","https://openalex.org/W2798542761","https://openalex.org/W2909948317","https://openalex.org/W2948672349","https://openalex.org/W2962677013","https://openalex.org/W2963150697","https://openalex.org/W2963849369","https://openalex.org/W2963857746","https://openalex.org/W2964015378","https://openalex.org/W2964236837","https://openalex.org/W2964241181","https://openalex.org/W2970987838","https://openalex.org/W2981537222","https://openalex.org/W2982161360","https://openalex.org/W2982770724","https://openalex.org/W2991405684","https://openalex.org/W2993182889","https://openalex.org/W3034428102","https://openalex.org/W3034681942","https://openalex.org/W3034826836","https://openalex.org/W3035049382","https://openalex.org/W3093600664","https://openalex.org/W3106546328","https://openalex.org/W3113410735","https://openalex.org/W3165312683","https://openalex.org/W4256561644","https://openalex.org/W6618372016","https://openalex.org/W6632100814","https://openalex.org/W6637373629","https://openalex.org/W6716109767","https://openalex.org/W6726873649","https://openalex.org/W6729508183","https://openalex.org/W6730410022","https://openalex.org/W6738964360","https://openalex.org/W6739778489","https://openalex.org/W6750697433","https://openalex.org/W6757911768","https://openalex.org/W6768489150","https://openalex.org/W6770414525","https://openalex.org/W6774611966","https://openalex.org/W6784930956"],"related_works":["https://openalex.org/W2382566571","https://openalex.org/W2349321798","https://openalex.org/W2366686860","https://openalex.org/W3036520466","https://openalex.org/W2350859087","https://openalex.org/W2387118502","https://openalex.org/W4233775131","https://openalex.org/W2391262724","https://openalex.org/W4231775656","https://openalex.org/W1986903754"],"abstract_inverted_index":{"Recent":[0],"state-of-the-art":[1],"one-stage":[2],"instance":[3,211],"segmentation":[4,212],"model":[5,109,158,188,219],"SOLO":[6,44,95,218],"divides":[7],"the":[8,82,98,104,114,157,187,210,243],"input":[9],"image":[10],"into":[11],"a":[12,87,151,180,217],"grid":[13,18,53,117,171],"and":[14,39,55,136,173,177,203],"directly":[15,76],"predicts":[16],"per":[17,116],"cell":[19,118],"object":[20,50,69,119],"masks":[21,47],"with":[22,140,199,220,230,242],"fully-convolutional":[23],"networks,":[24],"yielding":[25],"comparably":[26],"good":[27],"performance":[28,240],"as":[29,63],"traditional":[30],"two-stage":[31],"Mask":[32],"R-CNN":[33],"yet":[34],"enjoying":[35],"much":[36,161],"simpler":[37],"architecture":[38],"higher":[40,205],"efficiency.":[41,106],"We":[42,236],"observe":[43],"generates":[45],"similar":[46],"for":[48],"an":[49],"at":[51],"nearby":[52,134,170],"cells,":[54,172],"these":[56],"neighboring":[57,100,167],"predictions":[58],"can":[59],"complement":[60,137],"each":[61],"other":[62],"some":[64],"may":[65],"better":[66],"segment":[67],"certain":[68],"part,":[70],"most":[71],"of":[72,133],"which":[73],"are":[74],"however":[75],"discarded":[77],"by":[78,81,96,165,223],"non-maximum-suppression.":[79],"Motivated":[80],"observed":[83],"gap,":[84],"we":[85],"develop":[86],"novel":[88,148],"learning-based":[89],"aggregation":[90,143],"method":[91,144],"that":[92,129,155,185],"improves":[93,209],"upon":[94],"leveraging":[97],"rich":[99],"information":[101],"while":[102],"maintaining":[103],"architectural":[105],"The":[107,142],"resulting":[108],"is":[110,122],"named":[111],"SODAR.":[112],"Unlike":[113],"original":[115],"masks,":[120],"SODAR":[121,207],"implicitly":[123],"supervised":[124],"to":[125,159,189],"learn":[126],"mask":[127,152,163,197],"representations":[128,139,164,168,198],"encode":[130],"geometric":[131],"structure":[132],"objects":[135],"adjacent":[138],"context.":[141],"further":[145,237],"includes":[146],"two":[147],"designs:":[149],"1)":[150],"interpolation":[153],"mechanism":[154,184],"enables":[156],"generate":[160],"fewer":[162],"sharing":[166],"among":[169],"thus":[174,195],"saves":[175],"computation":[176],"memory;":[178],"2)":[179],"deformable":[181],"neighbour":[182],"sampling":[183,193],"allows":[186],"adaptively":[190],"adjust":[191],"neighbor":[192],"locations":[194],"gathering":[196],"more":[200],"relevant":[201],"context":[202],"achieving":[204],"performance.":[206],"significantly":[208],"performance,":[213],"e.g.,":[214],"it":[215],"outperforms":[216],"ResNet-101":[221],"backbone":[222],"2.2":[224],"AP":[225],"on":[226],"COCO":[227],"test":[228],"set,":[229],"only":[231],"about":[232],"3%":[233],"additional":[234],"computation.":[235],"show":[238],"consistent":[239],"gain":[241],"SOLOv2":[244],"model.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2021-12-31T00:00:00"}