{"id":"https://openalex.org/W4389667470","doi":"https://doi.org/10.1109/iros55552.2023.10342432","title":"Self-Supervised Instance Segmentation by Grasping","display_name":"Self-Supervised Instance Segmentation by Grasping","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667470","doi":"https://doi.org/10.1109/iros55552.2023.10342432"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342432","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/A5015663474","display_name":"YuXuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"YuXuan Liu","raw_affiliation_strings":["Covariant. ai","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Covariant. ai","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329900","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-0571-6177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Covariant. ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Covariant. ai","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["Covariant. ai","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Covariant. ai","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5614,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69191781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1162","last_page":"1169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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":0.9983999729156494,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9980000257492065,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9968000054359436,"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":0.6894701719284058},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6272919178009033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6066761612892151},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4803215563297272},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.41500118374824524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4092297852039337},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40627455711364746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894701719284058},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6272919178009033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6066761612892151},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4803215563297272},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.41500118374824524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4092297852039337},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40627455711364746}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342432","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1573546770","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2344939607","https://openalex.org/W2417256080","https://openalex.org/W2501210423","https://openalex.org/W2565639579","https://openalex.org/W2888845200","https://openalex.org/W2946952476","https://openalex.org/W2962791145","https://openalex.org/W2963150697","https://openalex.org/W3003224579","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3213165621","https://openalex.org/W4248936881","https://openalex.org/W4312259544","https://openalex.org/W4312615341","https://openalex.org/W4312815172","https://openalex.org/W4312829196","https://openalex.org/W4312933868","https://openalex.org/W4383109309","https://openalex.org/W4386071535","https://openalex.org/W6752823625","https://openalex.org/W6756257017","https://openalex.org/W6763293846","https://openalex.org/W6780327073"],"related_works":["https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W2945274617","https://openalex.org/W4313052709","https://openalex.org/W4298131179","https://openalex.org/W2375430703","https://openalex.org/W3199300986"],"abstract_inverted_index":{"Instance":[0],"segmentation":[1,21,26,61,125,149,177],"is":[2],"a":[3,12,29,59,64,82,128,159,170],"fundamental":[4],"skill":[5],"for":[6,23],"many":[7],"robotic":[8,172],"applications.":[9],"We":[10,120],"propose":[11],"self-supervised":[13],"method":[14,154],"that":[15,37,122],"uses":[16],"grasp":[17,60,79,91,124,183],"interactions":[18,92],"to":[19,70,116,189],"collect":[20],"supervision":[22],"an":[24,32,190],"instance":[25,118,148,176],"model.":[27],"When":[28],"robot":[30],"grasps":[31],"item,":[33],"the":[34,44,47,52,72,98,164,180],"mask":[35],"of":[36,46,67,90,166,182],"grasped":[38,73,86,100,134],"item":[39],"can":[40,84,103],"be":[41],"inferred":[42],"from":[43,63,75,88,106],"images":[45,69],"scene":[48],"before":[49,76],"and":[50,77,110],"after":[51,78],"grasp.":[53],"Leveraging":[54],"this":[55],"insight,":[56],"we":[57,102],"learn":[58],"model":[62,83,126,160,178],"small":[65],"dataset":[66],"labelled":[68],"segment":[71,85],"object":[74],"images.":[80],"Such":[81],"objects":[87,105,135],"thousands":[89],"without":[93],"costly":[94],"human":[95],"annotation.":[96],"Using":[97],"segmented":[99],"objects,":[101],"\u201ccut\u201d":[104],"their":[107],"original":[108],"scenes":[109,115],"\u201cpaste\u201d":[111],"them":[112],"into":[113],"new":[114],"generate":[117],"supervision.":[119],"show":[121],"our":[123,144,153,175],"provides":[127],"5x":[129],"error":[130],"reduction":[131],"when":[132],"segmenting":[133],"compared":[136,188],"with":[137,143,152,162],"traditional":[138],"image":[139,191],"subtraction":[140,192],"approaches.":[141],"Combined":[142],"\u201ccut-and-paste\u201d":[145],"generation":[146],"method,":[147],"models":[150],"trained":[151,161],"achieve":[155],"better":[156],"performance":[157],"than":[158],"10x":[163],"amount":[165],"labeled":[167],"data.":[168],"On":[169],"real":[171],"grasping":[173],"system,":[174],"reduces":[179],"rate":[181],"errors":[184],"by":[185],"over":[186],"3x":[187],"baseline.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}