{"id":"https://openalex.org/W4411232425","doi":"https://doi.org/10.1109/tpami.2025.3579469","title":"Unsupervised Pre-Training With Language-Vision Prompts for Low-Data Instance Segmentation","display_name":"Unsupervised Pre-Training With Language-Vision Prompts for Low-Data Instance Segmentation","publication_year":2025,"publication_date":"2025-06-12","ids":{"openalex":"https://openalex.org/W4411232425","doi":"https://doi.org/10.1109/tpami.2025.3579469","pmid":"https://pubmed.ncbi.nlm.nih.gov/40504713"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3579469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3579469","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":null,"display_name":"Dingwen Zhang","orcid":"https://orcid.org/0000-0001-8369-8886"},"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":"Dingwen Zhang","raw_affiliation_strings":["Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-8369-8886","affiliations":[{"raw_affiliation_string":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348569","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-2419-2700"},"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":"Hao Li","raw_affiliation_strings":["Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-2419-2700","affiliations":[{"raw_affiliation_string":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104313182","display_name":"Diqi He","orcid":null},"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":"Diqi He","raw_affiliation_strings":["Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0006-0607-8185","affiliations":[{"raw_affiliation_string":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377352","display_name":"Nian Liu","orcid":"https://orcid.org/0000-0002-0825-6081"},"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"]},{"id":"https://openalex.org/I4210116052","display_name":"Inception Institute of Artificial Intelligence","ror":"https://ror.org/02664zk40","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210116052"]}],"countries":["AE","CN"],"is_corresponding":false,"raw_author_name":"Nian Liu","raw_affiliation_strings":["Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","Inception Institute of Artificial Intelligence, UAE"],"raw_orcid":"https://orcid.org/0000-0002-0825-6081","affiliations":[{"raw_affiliation_string":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Inception Institute of Artificial Intelligence, UAE","institution_ids":["https://openalex.org/I4210116052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060524512","display_name":"Lechao Cheng","orcid":"https://orcid.org/0000-0002-7546-9052"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lechao Cheng","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7546-9052","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075880303","display_name":"Jingdong Wang","orcid":"https://orcid.org/0000-0002-4888-4445"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Wang","raw_affiliation_strings":["Department of Computer Vision, Baidu Inc, Beijing, China","Department of Computer Vision, Baidu Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision, Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Department of Computer Vision, Baidu Inc, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012529382","display_name":"Junwei Han","orcid":"https://orcid.org/0000-0001-5545-7217"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Han","raw_affiliation_strings":["School of Artifical Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China","School of Artifical Intelligence, Chongqing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0001-5545-7217","affiliations":[{"raw_affiliation_string":"School of Artifical Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Artifical Intelligence, Chongqing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.5462,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.98627862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"47","issue":"10","first_page":"8642","last_page":"8657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9569000005722046,"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":0.9569000005722046,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9125000238418579,"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":0.7514216303825378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7330580353736877},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5702874064445496},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5130432844161987},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4947482943534851},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46668797731399536},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4579455256462097},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44033530354499817},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42317143082618713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3474045991897583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7514216303825378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7330580353736877},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5702874064445496},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5130432844161987},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4947482943534851},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46668797731399536},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4579455256462097},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44033530354499817},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42317143082618713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3474045991897583},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3579469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3579469","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:40504713","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40504713","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":[],"awards":[{"id":"https://openalex.org/G2513888872","display_name":null,"funder_award_id":"62106235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3364597423","display_name":null,"funder_award_id":"62472139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G376329712","display_name":null,"funder_award_id":"2022ZD0119004","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G4112834733","display_name":null,"funder_award_id":"62293543","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6408364431","display_name":null,"funder_award_id":"U21B2048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8584449773","display_name":null,"funder_award_id":"62136007","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2088049833","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2317851288","https://openalex.org/W2340897893","https://openalex.org/W2565639579","https://openalex.org/W2963150697","https://openalex.org/W2982161360","https://openalex.org/W2982770724","https://openalex.org/W2996583130","https://openalex.org/W3019728440","https://openalex.org/W3034890557","https://openalex.org/W3096609285","https://openalex.org/W3113410735","https://openalex.org/W3117854388","https://openalex.org/W3122006940","https://openalex.org/W3132018008","https://openalex.org/W3152635971","https://openalex.org/W3165924482","https://openalex.org/W3168649818","https://openalex.org/W3168822201","https://openalex.org/W3169575272","https://openalex.org/W3172752666","https://openalex.org/W3198377975","https://openalex.org/W4214561053","https://openalex.org/W4214613769","https://openalex.org/W4312458986","https://openalex.org/W4312548937","https://openalex.org/W4312651322","https://openalex.org/W4312815172","https://openalex.org/W4312910992","https://openalex.org/W4312912313","https://openalex.org/W4313145515","https://openalex.org/W4382202923","https://openalex.org/W4386065835","https://openalex.org/W4386075648","https://openalex.org/W4386076493","https://openalex.org/W4390872133","https://openalex.org/W4390873543","https://openalex.org/W4390874207","https://openalex.org/W4391952636","https://openalex.org/W4402275786","https://openalex.org/W4402715795"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W4394050964","https://openalex.org/W1522196789","https://openalex.org/W2551249631"],"abstract_inverted_index":{"In":[0],"recent":[1],"times,":[2],"following":[3],"the":[4,31,58,87,145,163,171,203],"paradigm":[5],"of":[6,33,118,173],"DETR":[7],"(DEtection":[8],"TRansformer),":[9],"query-based":[10],"end-to-end":[11],"instance":[12,107],"segmentation":[13,108],"(QEIS)":[14],"methods":[15,36],"have":[16],"exhibited":[17],"superior":[18],"performance":[19,206],"compared":[20],"to":[21,55,113,127,151,166],"CNN-based":[22,186],"models,":[23],"particularly":[24],"when":[25,39,211],"trained":[26],"on":[27,51,132,194],"large-scale":[28],"datasets.":[29],"Nevertheless,":[30],"effectiveness":[32],"these":[34],"QEIS":[35,105,177,204],"diminishes":[37],"significantly":[38,209],"confronted":[40],"with":[41,99,213],"limited":[42],"training":[43],"data.":[44],"This":[45],"limitation":[46],"arises":[47],"from":[48],"their":[49,152],"reliance":[50],"substantial":[52],"data":[53],"volumes":[54],"effectively":[56],"train":[57],"pivotal":[59],"queries/kernels":[60],"that":[61,202],"are":[62],"essential":[63],"for":[64,79,160],"acquiring":[65],"localization":[66,147],"and":[67,143,148,182,198],"shape":[68,149],"priors.":[69],"To":[70],"address":[71],"this":[72],"problem,":[73],"we":[74,92],"propose":[75],"a":[76,94],"novel":[77],"method":[78,116],"unsupervised":[80],"pre-training":[81,161,175],"in":[82,188],"low-data":[83,189],"regimes.":[84,190],"Inspired":[85],"by":[86,109],"recently":[88],"successful":[89],"prompting":[90],"technique,":[91],"introduce":[93],"new":[95],"method,":[96,176],"Unsupervised":[97],"Pre-training":[98],"Language-Vision":[100],"Prompts":[101],"(UPLVP),":[102],"which":[103],"improves":[104],"models'":[106,205],"bringing":[110],"language-vision":[111,125],"prompts":[112,142],"queries/kernels.":[114],"Our":[115],"consists":[117],"three":[119],"parts:":[120],"(1)":[121],"Masks":[122],"Proposal:":[123],"Utilizes":[124],"models":[126,178,187],"generate":[128],"pseudo":[129,139],"masks":[130,140],"based":[131],"unlabeled":[133],"images.":[134],"(2)":[135],"Prompt-Kernel":[136],"Matching:":[137],"Converts":[138],"into":[141],"injects":[144],"best-matched":[146],"features":[150],"corresponding":[153],"kernels.":[154],"(3)":[155],"Kernel":[156],"Supervision:":[157],"Formulates":[158],"supervision":[159],"at":[162],"kernel":[164],"level":[165],"ensure":[167],"robust":[168],"learning.":[169],"With":[170],"help":[172],"our":[174,214],"can":[179,207],"converge":[180],"faster":[181],"perform":[183],"better":[184],"than":[185],"Experimental":[191],"evaluations":[192],"conducted":[193],"MS":[195],"COCO,":[196],"Cityscapes,":[197],"CTW1500":[199],"datasets":[200],"indicate":[201],"be":[208],"improved":[210],"pre-trained":[212],"method.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}