{"id":"https://openalex.org/W7141720543","doi":"https://doi.org/10.1109/tpami.2026.3673339","title":"Prompt is All You Need: Prompting Foundation Models for Large-Scale Self-Supervised Semantic Segmentation","display_name":"Prompt is All You Need: Prompting Foundation Models for Large-Scale Self-Supervised Semantic Segmentation","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7141720543","doi":"https://doi.org/10.1109/tpami.2026.3673339","pmid":"https://pubmed.ncbi.nlm.nih.gov/41894211"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3673339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3673339","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5088492442","display_name":"Jiaojiao Su","orcid":"https://orcid.org/0000-0002-2115-0978"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaojiao Su","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2115-0978","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiwu Luo","orcid":"https://orcid.org/0000-0003-2822-5538"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwu Luo","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2822-5538","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077549875","display_name":"Shuzhou Sun","orcid":"https://orcid.org/0000-0001-8453-3346"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhou Sun","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8453-3346","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062441362","display_name":"Yuenan Hou","orcid":"https://orcid.org/0000-0002-2844-7416"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuenan Hou","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2844-7416","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6807-049X","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072890921","display_name":"Janne Heikkil\u00e4","orcid":"https://orcid.org/0000-0003-0073-0866"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Janne Heikkil\u00e4","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis (CMVS), the University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-0073-0866","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis (CMVS), the University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130769523","display_name":"Chunhua Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua Yang","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3770-9887","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130760513","display_name":"Li Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2011-2873","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36754487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"8642","last_page":"8660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2168000042438507,"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/T10028","display_name":"Topic Modeling","score":0.2168000042438507,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.15209999680519104,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09769999980926514,"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":0.531499981880188},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4169999957084656},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38960000872612},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29109999537467957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720300018787384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6394000053405762},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4251999855041504},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4169999957084656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3673339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3673339","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41894211","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41894211","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.42699357867240906}],"awards":[{"id":"https://openalex.org/G1938939197","display_name":null,"funder_award_id":"62322317","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5747617250","display_name":null,"funder_award_id":"62531026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5839471878","display_name":null,"funder_award_id":"62027811","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G592884138","display_name":null,"funder_award_id":"62394340","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6810672901","display_name":null,"funder_award_id":"62573433","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7774348999","display_name":null,"funder_award_id":"62376283","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,74,162],"paper":[1],"addresses":[2,103],"the":[3,16,21,28,104,146,151,171,188],"important":[4],"and":[5,34,68,80,127,195,202,216],"challenging":[6],"task":[7,32],"of":[8,23,107],"large-scale":[9],"unsupervised":[10],"semantic":[11,79,116],"segmentation":[12],"(LUSS).":[13],"We":[14],"present":[15,40,149],"first":[17],"attempt":[18],"to":[19,39,170,238],"unleash":[20],"power":[22],"foundation":[24,50,152,172,236],"models":[25,51,153,237],"(FMs)":[26],"for":[27,46,52,83,199,224,234],"challenging,":[29],"dense":[30],"prediction":[31],"LUSS,":[33,47],"our":[35],"main":[36],"objective":[37],"is":[38],"simple,":[41],"effective":[42],"yet":[43],"efficient":[44],"solutions":[45],"namely":[48],"Prompting":[49],"LUSS":[53],"(PLUSS).":[54],"Firstly,":[55],"we":[56,99],"proposed":[57,228],"a":[58,71,86,115,128,231],"cascade":[59,75],"framework":[60,229],"PLUSS$_\\alpha$\u03b1":[61],"by":[62,143,192],"effectively":[63],"marrying":[64],"CLIPS,":[65],"Grounding":[66],"DINO,":[67],"SAM":[69],"in":[70,197],"zero-shot":[72],"manner.":[73],"architecture":[76],"automatically":[77],"generates":[78],"spatial":[81],"prompts":[82],"SAM,":[84],"establishing":[85],"strong":[87,221],"baseline":[88,233],"that":[89,118,131,181],"significantly":[90],"outperforms":[91],"previous":[92,189],"state-of-the-art":[93],"methods.":[94],"Building":[95],"upon":[96],"this":[97],"foundation,":[98],"propose":[100],"PLUSS$_\\beta$\u03b2,":[101],"which":[102],"critical":[105],"bottleneck":[106],"prompt":[108,125],"quality":[109],"through":[110,135],"two":[111],"novel":[112],"tuner":[113,117,130],"modules:":[114],"enhances":[119],"fine-grained":[120],"category":[121],"discrimination":[122],"via":[123],"visual":[124],"tuning,":[126],"box":[129],"improves":[132],"object":[133,214],"localization":[134],"cross-modal":[136],"feature":[137],"fusion.":[138],"Both":[139],"tuners":[140],"are":[141],"optimized":[142],"capitalizing":[144],"on":[145,177],"knowledge":[147],"already":[148],"within":[150],"themselves,":[154],"deriving":[155],"self-supervised":[156],"signals":[157],"from":[158],"internal":[159],"model":[160],"consistency.":[161],"approach":[163,207],"requires":[164],"no":[165],"external":[166],"supervision":[167],"or":[168],"updates":[169],"models'":[173],"parameters.":[174],"Extensive":[175],"experiments":[176],"ImageNet-S":[178],"benchmarks":[179],"demonstrate":[180],"PLUSS$_\\beta$\u03b2":[182],"achieves":[183],"remarkable":[184],"performance":[185],"improvements,":[186],"surpassing":[187],"best":[190],"method":[191],"39.6%,":[193],"27.3%,":[194],"22.6%":[196],"mIoU":[198],"50,":[200],"300,":[201],"919":[203],"categories":[204],"respectively.":[205],"Our":[206],"exhibits":[208],"robust":[209],"category-shape":[210],"representation":[211],"across":[212],"varying":[213],"sizes":[215],"dataset":[217],"scales,":[218],"while":[219],"maintaining":[220],"generalization":[222],"capabilities":[223],"open-vocabulary":[225],"tasks.":[226,241],"The":[227],"provides":[230],"solid":[232],"adapting":[235],"downstream":[239],"vision":[240]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-28T00:00:00"}