{"id":"https://openalex.org/W7124152295","doi":"https://doi.org/10.1109/tip.2026.3652371","title":"EinsPT: Efficient Instance-Aware Pre-Training of Vision Foundation Models","display_name":"EinsPT: Efficient Instance-Aware Pre-Training of Vision Foundation Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124152295","doi":"https://doi.org/10.1109/tip.2026.3652371","pmid":"https://pubmed.ncbi.nlm.nih.gov/41533629"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3652371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3652371","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","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/A5121240268","display_name":"Zhaozhi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaozhi Wang","raw_affiliation_strings":["School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069782593","display_name":"Yunjie Tian","orcid":"https://orcid.org/0000-0002-5103-3748"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjie Tian","raw_affiliation_strings":["School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxi Xie","raw_affiliation_strings":["Huawei Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123023782","display_name":"Yaowei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qixiang Ye","orcid":"https://orcid.org/0000-0003-1215-6259"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiang Ye","raw_affiliation_strings":["School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121240268"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12880086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"786","last_page":"799"},"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":0.38339999318122864,"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":0.38339999318122864,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.12460000067949295,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0997999981045723,"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/code","display_name":"Code (set theory)","score":0.4507000148296356},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4390999972820282},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.430400013923645},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4171999990940094},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3815000057220459},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3603000044822693},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6105999946594238},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4507000148296356},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3652371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3652371","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41533629","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41533629","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.743070662021637}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2340897893","https://openalex.org/W2565639579","https://openalex.org/W2737258237","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963420272","https://openalex.org/W2983943451","https://openalex.org/W3035422918","https://openalex.org/W3035524453","https://openalex.org/W3037492894","https://openalex.org/W3096609285","https://openalex.org/W3128661784","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W3160694286","https://openalex.org/W3165924482","https://openalex.org/W3168822201","https://openalex.org/W3174415835","https://openalex.org/W3177096435","https://openalex.org/W4214614183","https://openalex.org/W4295308583","https://openalex.org/W4312312750","https://openalex.org/W4312349930","https://openalex.org/W4312804044","https://openalex.org/W4312847199","https://openalex.org/W4313156423","https://openalex.org/W4386071535","https://openalex.org/W4386075739","https://openalex.org/W4386076174","https://openalex.org/W4390874177","https://openalex.org/W4400721967","https://openalex.org/W4401633581","https://openalex.org/W4406821408","https://openalex.org/W4406902947","https://openalex.org/W4409262252","https://openalex.org/W4409262773","https://openalex.org/W4409366433","https://openalex.org/W4413147663","https://openalex.org/W4414110709"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,55],"study,":[2],"we":[3,57],"introduce":[4],"EinsPT,":[5],"an":[6],"efficient":[7],"instance-aware":[8],"pre-training":[9,28],"paradigm":[10],"designed":[11],"to":[12,43,88],"reduce":[13],"the":[14,68],"transfer":[15],"gap":[16],"between":[17],"vision":[18],"foundation":[19,69],"models":[20],"and":[21,40,50,65,100,133],"downstream":[22,118],"instance-level":[23,101],"tasks.":[24],"Unlike":[25],"conventional":[26],"image-level":[27],"that":[29,46,62,110],"relies":[30],"solely":[31],"on":[32,84,104],"unlabeled":[33],"images,":[34],"EinsPT":[35,111],"leverages":[36],"both":[37],"image":[38],"reconstruction":[39,99],"instance":[41,51,131],"annotations":[42],"learn":[44],"representations":[45],"are":[47,95],"spatially":[48],"coherent":[49],"discriminative.":[52],"To":[53],"achieve":[54],"efficiently,":[56],"propose":[58],"a":[59,79],"proxy-foundation":[60],"architecture":[61],"decouples":[63],"high-resolution":[64,86],"low-resolution":[66,73],"learning:":[67],"model":[70,82],"processes":[71],"masked":[72],"images":[74,87],"for":[75],"global":[76],"semantics,":[77],"while":[78,125],"lightweight":[80],"proxy":[81],"operates":[83],"complete":[85],"preserve":[89],"fine-grained":[90],"details.":[91],"The":[92],"two":[93],"branches":[94],"jointly":[96],"optimized":[97],"through":[98],"prediction":[102],"losses":[103],"fused":[105],"features.":[106],"Extensive":[107],"experiments":[108],"demonstrate":[109],"consistently":[112],"enhances":[113],"recognition":[114],"accuracy":[115],"across":[116],"various":[117],"tasks":[119],"with":[120],"substantially":[121],"reduced":[122],"computational":[123],"cost,":[124],"qualitative":[126],"results":[127],"further":[128],"reveal":[129],"improved":[130],"perception":[132],"completeness":[134],"in":[135],"visual":[136],"representations.":[137],"Code":[138],"is":[139],"available":[140],"at":[141],"github.com/feufhd/EinsPT.":[142]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-15T00:00:00"}