{"id":"https://openalex.org/W7138014230","doi":"https://doi.org/10.1609/aaai.v40i13.38105","title":"S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything Without Supervision","display_name":"S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything Without Supervision","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138014230","doi":"https://doi.org/10.1609/aaai.v40i13.38105"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38105","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38105","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38105","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129747098","display_name":"Huihui Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huihui Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659803","display_name":"Jin Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Ye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074311923","display_name":"Hongqiu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongqiu Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111097611","display_name":"Changkai Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changkai Ji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683354","display_name":"Jiashi Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiashi Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706057","display_name":"Ming Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040971828","display_name":"Ziyan Huang","orcid":"https://orcid.org/0000-0002-1533-5239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyan Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129679805","display_name":"Ying Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659206","display_name":"Chenglong Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenglong Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003869833","display_name":"Tianbin Li","orcid":"https://orcid.org/0009-0001-3617-8324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianbin Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129682946","display_name":"Lihao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihao Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129673668","display_name":"Junjun He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjun He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129721060","display_name":"Lei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5129747098"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29306488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"11250","last_page":"11258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8858000040054321,"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":0.8858000040054321,"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":0.06030000001192093,"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":0.006099999882280827,"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/segmentation","display_name":"Segmentation","score":0.7218000292778015},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6816999912261963},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6644999980926514},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6039000153541565},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.47209998965263367},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43320000171661377},{"id":"https://openalex.org/keywords/pretext","display_name":"Pretext","score":0.423799991607666},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.38989999890327454},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.388700008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915999889373779},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7218000292778015},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6816999912261963},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6644999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051999926567078},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4805000126361847},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.388700008392334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3070000112056732},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38105","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38105","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38105","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38105","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"self-supervised":[1],"image":[2],"segmentation":[3,11],"models":[4],"have":[5],"achieved":[6],"promising":[7],"performance":[8,184],"on":[9,104,160,163,166,169,186],"semantic":[10],"and":[12,91,93,120],"class-agnostic":[13],"instance":[14],"segmentation.":[15],"However,":[16],"their":[17],"pretraining":[18],"schedule":[19],"is":[20,135],"multi-stage,":[21],"requiring":[22],"a":[23,65,118,121,175],"time-consuming":[24,33],"pseudo-masks":[25,95],"generation":[26],"process":[27,35],"between":[28],"each":[29],"training":[30,44],"epoch.":[31],"This":[32],"offline":[34],"not":[36],"only":[37],"makes":[38],"it":[39],"difficult":[40],"to":[41,50,54,87,137,140,174],"scale":[42],"with":[43],"dataset":[45],"size,":[46],"but":[47],"also":[48],"leads":[49],"sub-optimal":[51],"solutions":[52],"due":[53],"its":[55],"discontinuous":[56],"optimization":[57],"routine.":[58],"To":[59],"solve":[60],"these,":[61],"we":[62,108],"first":[63],"present":[64],"novel":[66,128],"pseudo-mask":[67],"algorithm,":[68],"Fast":[69],"Universal":[70,113],"Agglomerative":[71],"Pooling":[72],"(UniAP).":[73],"Each":[74],"layer":[75],"of":[76,81,98,158,179],"UniAP":[77],"can":[78],"identify":[79],"groups":[80],"similar":[82],"nodes":[83],"in":[84],"parallel,":[85],"allowing":[86],"generate":[88],"both":[89],"semantic-level":[90],"instance-level":[92],"multi-granular":[94],"within":[96],"ens":[97],"milliseconds":[99],"for":[100,124],"one":[101],"image.":[102],"Based":[103],"the":[105,110,142,146,151],"fast":[106],"UniAP,":[107],"propose":[109],"Scalable":[111],"Self-Supervised":[112],"Segmentation":[114],"(S2-UniSeg),":[115],"which":[116],"employs":[117],"student":[119],"momentum":[122],"teacher":[123],"continuous":[125],"pretraining.":[126],"A":[127],"segmentation-oriented":[129],"pretext":[130],"task,":[131],"Query-wise":[132],"Self-Distillation":[133],"(QuerySD),":[134],"proposed":[136],"pretrain":[138],"S2-UniSeg":[139,149,181],"learn":[141],"local-to-global":[143],"correspondences.":[144],"Under":[145],"same":[147],"setting,":[148],"outperforms":[150],"SOTA":[152],"UnSAM":[153],"model,":[154],"achieving":[155],"notable":[156],"improvements":[157],"AP+6.9":[159],"COCO,":[161],"AR+11.1":[162],"UVO,":[164],"PixelAcc+4.5":[165],"COCOStuff-27,":[167],"RQ+8.0":[168],"Cityscapes.":[170],"After":[171],"scaling":[172],"up":[173],"larger":[176],"2M-image":[177],"subset":[178],"SA-1B,":[180],"further":[182],"achieves":[183],"gains":[185],"all":[187],"four":[188],"benchmarks.":[189]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}