{"id":"https://openalex.org/W4387969219","doi":"https://doi.org/10.1145/3581783.3612493","title":"Transformer-based Open-world Instance Segmentation with Cross-task Consistency Regularization","display_name":"Transformer-based Open-world Instance Segmentation with Cross-task Consistency Regularization","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969219","doi":"https://doi.org/10.1145/3581783.3612493"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033413041","display_name":"Xizhe Xue","orcid":"https://orcid.org/0000-0001-8636-3993"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xizhe Xue","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8636-3993","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039427501","display_name":"Dongdong Yu","orcid":"https://orcid.org/0000-0002-4967-022X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongdong Yu","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4967-022X","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070976480","display_name":"Lingqiao Liu","orcid":"https://orcid.org/0000-0003-3584-795X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3584-795X","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089042848","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-0139-0536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0139-0536","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115501011","display_name":"Satoshi Tsutsui","orcid":"https://orcid.org/0000-0001-8003-2616"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Satoshi Tsutsui","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8003-2616","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785617","display_name":"Ying Li","orcid":"https://orcid.org/0000-0001-7370-1754"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7370-1754","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039592275","display_name":"Zehuan Yuan","orcid":"https://orcid.org/0000-0002-0349-9367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehuan Yuan","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0349-9367","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ping Song","orcid":"https://orcid.org/0000-0002-3353-1444"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Song","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3353-1444","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"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":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7681-2166","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2507","last_page":"2515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7676354050636292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7175177931785583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.606856644153595},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5909820795059204},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5207409858703613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47624826431274414},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.47390806674957275},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.46477702260017395},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45879504084587097},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.42759090662002563},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.41147804260253906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3798675835132599},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.3669933080673218}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7676354050636292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175177931785583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.606856644153595},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5909820795059204},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5207409858703613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47624826431274414},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.47390806674957275},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.46477702260017395},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45879504084587097},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.42759090662002563},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.41147804260253906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3798675835132599},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3669933080673218}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612493","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3663414317","display_name":null,"funder_award_id":"NRF-NRFF13-2021-0008","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G3968842904","display_name":null,"funder_award_id":"NRF-NRFF13-2021-0008","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G6556306731","display_name":null,"funder_award_id":"62271400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2216125271","https://openalex.org/W2340897893","https://openalex.org/W2753709519","https://openalex.org/W2781228439","https://openalex.org/W2963150697","https://openalex.org/W2963921921","https://openalex.org/W2981793666","https://openalex.org/W2993182889","https://openalex.org/W3034225195","https://openalex.org/W3034681942","https://openalex.org/W3096609285","https://openalex.org/W3106651317","https://openalex.org/W3113410735","https://openalex.org/W3138516171","https://openalex.org/W3158120491","https://openalex.org/W3167120888","https://openalex.org/W3167260844","https://openalex.org/W3168783492","https://openalex.org/W3180659539","https://openalex.org/W3184439416","https://openalex.org/W3213165621","https://openalex.org/W4214613769","https://openalex.org/W4287992790","https://openalex.org/W4312444067","https://openalex.org/W4312894362","https://openalex.org/W4312940821","https://openalex.org/W4313189668","https://openalex.org/W6796402304"],"related_works":["https://openalex.org/W3039174484","https://openalex.org/W4287728368","https://openalex.org/W3144569342","https://openalex.org/W2185902295","https://openalex.org/W2945274617","https://openalex.org/W2372421320","https://openalex.org/W2057775483","https://openalex.org/W2041871225","https://openalex.org/W2386644571","https://openalex.org/W2387793296"],"abstract_inverted_index":{"Open-World":[0],"Instance":[1],"Segmentation":[2],"(OWIS)":[3],"is":[4],"an":[5,138,148],"emerging":[6],"research":[7],"topic":[8],"that":[9,53,106,131,144,151,164],"aims":[10],"to":[11,87,95,98,137,141,178],"segment":[12],"class-agnostic":[13,72],"object":[14,31,73,153],"instances":[15],"from":[16],"images.":[17,159],"The":[18],"mainstream":[19],"approaches":[20],"use":[21,92],"a":[22,45,84,100,108,120],"two-stage":[23],"segmentation":[24,80,97],"framework,":[25,81],"which":[26],"first":[27],"locates":[28],"the":[29,54,59,69,77,113,124,132,165,181,186],"candidate":[30],"bounding":[32],"boxes":[33],"and":[34,91,174,197],"then":[35],"performs":[36],"instance":[37,79,96,117],"segmentation.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,82],"instead":[43],"promote":[44],"single-stage":[46,60],"transformer-based":[47,78],"framework":[48,61],"for":[49,66,157],"OWIS.":[50],"We":[51,104,128],"argue":[52],"end-to-end":[55],"training":[56],"process":[57],"in":[58,123,171,191,199],"can":[62],"be":[63,146],"more":[64],"convenient":[65],"directly":[67],"regularizing":[68],"localization":[70],"of":[71,115],"pixels.":[74],"Based":[75],"on":[76],"propose":[83],"regularization":[85],"model":[86],"predict":[88],"foreground":[89],"pixels":[90],"its":[93],"relation":[94],"construct":[99],"cross-task":[101],"consistency":[102,109],"loss.":[103],"show":[105,130],"such":[107],"loss":[110,134],"could":[111,145],"alleviate":[112],"problem":[114,122],"incomplete":[116],"annotation":[118],"-":[119],"common":[121],"existing":[125],"OWIS":[126,143],"datasets.":[127],"also":[129],"proposed":[133,166,182],"lends":[135],"itself":[136],"effective":[139],"solution":[140],"semi-supervised":[142,175],"considered":[147],"extreme":[149],"case":[150],"all":[152],"annotations":[154],"are":[155],"absent":[156],"some":[158],"Our":[160],"extensive":[161],"experiments":[162],"demonstrate":[163],"method":[167,183],"achieves":[168],"impressive":[169],"results":[170],"both":[172],"fully-supervised":[173],"settings.":[176],"Compared":[177],"SOTA":[179],"methods,":[180],"significantly":[184],"improves":[185],"AP_100":[187],"score":[188],"by":[189],"4.75%":[190],"UVO":[192],"dataset":[193,195,201,203],"\u2192UVO":[194,202],"setting":[196],"4.05%":[198],"COCO":[200],"setting.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}