{"id":"https://openalex.org/W4223978083","doi":"https://doi.org/10.48550/arxiv.2204.06107","title":"Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity","display_name":"Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity","publication_year":2022,"publication_date":"2022-04-12","ids":{"openalex":"https://openalex.org/W4223978083","doi":"https://doi.org/10.48550/arxiv.2204.06107"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2204.06107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.06107","pdf_url":"https://arxiv.org/pdf/2204.06107","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.06107","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041890745","display_name":"Weiyao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Weiyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055620900","display_name":"Matt Feiszli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiszli, Matt","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453966","display_name":"Heng Wang","orcid":"https://orcid.org/0000-0002-8309-9645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Heng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001594573","display_name":"Jitendra Malik","orcid":"https://orcid.org/0000-0003-3695-1580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malik, Jitendra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016319243","display_name":"Du Tran","orcid":"https://orcid.org/0000-0001-9673-7194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Du","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041890745"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9825000166893005,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9825000166893005,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9739000201225281,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.968500018119812,"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":0.7485756874084473},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7189176678657532},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6907000541687012},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6372376084327698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.591577410697937},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5260205864906311},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44198086857795715},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4356478154659271},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42920297384262085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.372027188539505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32344168424606323},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07926508784294128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485756874084473},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7189176678657532},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6907000541687012},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6372376084327698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.591577410697937},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5260205864906311},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44198086857795715},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4356478154659271},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42920297384262085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.372027188539505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32344168424606323},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07926508784294128}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2204.06107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.06107","pdf_url":"https://arxiv.org/pdf/2204.06107","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2204.06107","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.06107","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.06107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.06107","pdf_url":"https://arxiv.org/pdf/2204.06107","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4223978083.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W4388145910","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2807634898","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W1997160662"],"abstract_inverted_index":{"Open-world":[0],"instance":[1,117,122,134],"segmentation":[2,135],"is":[3,17,146],"the":[4,75,80,130],"task":[5],"of":[6,61,99,115],"grouping":[7],"pixels":[8],"into":[9],"object":[10],"instances":[11],"without":[12,52],"any":[13],"pre-determined":[14],"taxonomy.":[15],"This":[16],"challenging,":[18],"as":[19,77,79],"state-of-the-art":[20],"methods":[21],"rely":[22],"on":[23,132,136,148],"explicit":[24],"class":[25],"semantics":[26],"obtained":[27],"from":[28],"large":[29,113],"labeled":[30],"datasets,":[31],"and":[32,127,143],"out-of-domain":[33],"evaluation":[34],"performance":[35],"drops":[36],"significantly.":[37],"Here":[38],"we":[39,110,124],"propose":[40],"a":[41,58,69,86,93,112],"novel":[42],"approach":[43,56],"for":[44,88],"mask":[45,66],"proposals,":[46],"Generic":[47],"Grouping":[48],"Networks":[49],"(GGNs),":[50],"constructed":[51],"semantic":[53],"supervision.":[54],"Our":[55],"combines":[57],"local":[59,95],"measure":[60],"pixel":[62],"affinity":[63],"with":[64,120],"instance-level":[65],"supervision,":[67],"producing":[68],"training":[70],"regimen":[71],"designed":[72],"to":[73,105],"make":[74],"model":[76],"generic":[78],"data":[81],"diversity":[82],"allows.":[83],"We":[84],"introduce":[85],"method":[87],"predicting":[89],"Pairwise":[90],"Affinities":[91],"(PA),":[92],"learned":[94],"relationship":[96],"between":[97],"pairs":[98],"pixels.":[100],"PA":[101,109],"generalizes":[102],"very":[103],"well":[104],"unseen":[106],"categories.":[107],"From":[108],"construct":[111],"set":[114],"pseudo-ground-truth":[116],"masks;":[118],"combined":[119],"human-annotated":[121],"masks":[123],"train":[125],"GGNs":[126],"significantly":[128],"outperform":[129],"SOTA":[131],"open-world":[133],"various":[137],"benchmarks":[138],"including":[139],"COCO,":[140],"LVIS,":[141],"ADE20K,":[142],"UVO.":[144],"Code":[145],"available":[147],"project":[149],"website:":[150],"https://sites.google.com/view/generic-grouping/.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}