{"id":"https://openalex.org/W4414265861","doi":"https://doi.org/10.1109/tgrs.2025.3610687","title":"MVFG: Enhancing Semantic Segmentation via Mix Vision Transformer With a Feature Guidance Module Powered by SAM Masks","display_name":"MVFG: Enhancing Semantic Segmentation via Mix Vision Transformer With a Feature Guidance Module Powered by SAM Masks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414265861","doi":"https://doi.org/10.1109/tgrs.2025.3610687"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3610687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3610687","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Bo Zhao","orcid":"https://orcid.org/0009-0006-6378-6188"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0006-6378-6188","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012917910","display_name":"Tieming Wu","orcid":"https://orcid.org/0009-0005-1584-0277"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingzhang Wu","raw_affiliation_strings":["State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039509820","display_name":"Xianyun Wu","orcid":"https://orcid.org/0000-0002-4450-3801"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianyun Wu","raw_affiliation_strings":["State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-4450-3801","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085919297","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0003-1679-3271"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Hangzhou Institute of Technology, Xidian University, Xi&#x2019;an, China","Hangzhou institute of technology, Xidian University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Institute of Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Hangzhou institute of technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067798266","display_name":"Yunsong Li","orcid":"https://orcid.org/0000-0002-0234-6270"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsong Li","raw_affiliation_strings":["State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-0234-6270","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lantao Feng","orcid":"https://orcid.org/0009-0002-9649-2726"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantao Feng","raw_affiliation_strings":["Hangzhou Institute of Technology, Xidian University, Xi&#x2019;an, China","Hangzhou institute of technology, Xidian University, China"],"raw_orcid":"https://orcid.org/0009-0002-9649-2726","affiliations":[{"raw_affiliation_string":"Hangzhou Institute of Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Hangzhou institute of technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024800495","display_name":"Haoxin Chen","orcid":"https://orcid.org/0009-0000-6085-2107"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxin Chen","raw_affiliation_strings":["State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Service Networks, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104027915","display_name":"Dan Li","orcid":"https://orcid.org/0000-0001-8956-9604"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Li","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060262250","display_name":"Bormin Huang","orcid":"https://orcid.org/0000-0001-8275-9536"},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bormin Huang","raw_affiliation_strings":["Intel Parallel Computing Center, University of Wisconsin&#x2013;Madison, Madison, US","Intel Parallel Computing Center and University of Wisconsin-Madison, USA"],"raw_orcid":"https://orcid.org/0000-0001-8275-9536","affiliations":[{"raw_affiliation_string":"Intel Parallel Computing Center, University of Wisconsin&#x2013;Madison, Madison, US","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"Intel Parallel Computing Center and University of Wisconsin-Madison, USA","institution_ids":["https://openalex.org/I4210131745"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7508993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.8986999988555908,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.8986999988555908,"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/T13382","display_name":"Robotics and Automated Systems","score":0.8967999815940857,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.8873999714851379,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7409999966621399},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4918999969959259},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.45809999108314514},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43700000643730164},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.40529999136924744},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38670000433921814},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3862000107765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420000076293945},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7409999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431999802589417},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5418000221252441},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4918999969959259},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43700000643730164},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3181000053882599},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.25769999623298645},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3610687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3610687","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1595715893","display_name":null,"funder_award_id":"B08038","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G7796495234","display_name":null,"funder_award_id":"62535015","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/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2139577851","https://openalex.org/W2412782625","https://openalex.org/W2464755555","https://openalex.org/W2778539913","https://openalex.org/W2787091153","https://openalex.org/W2884822772","https://openalex.org/W2963659230","https://openalex.org/W3008297566","https://openalex.org/W3034427230","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3141797743","https://openalex.org/W3161825146","https://openalex.org/W3168997536","https://openalex.org/W3175515048","https://openalex.org/W3185341429","https://openalex.org/W4214893857","https://openalex.org/W4318149001","https://openalex.org/W4385245566","https://openalex.org/W4388129777","https://openalex.org/W4388430265","https://openalex.org/W4390874575","https://openalex.org/W4391021462","https://openalex.org/W4391852066","https://openalex.org/W4391991763","https://openalex.org/W4392910325","https://openalex.org/W4393160910","https://openalex.org/W4394597311","https://openalex.org/W4404481310","https://openalex.org/W4408353726"],"related_works":[],"abstract_inverted_index":{"The":[0,53,120],"challenges":[1],"in":[2,14,127],"semantic":[3,32,66,115,121,125],"segmentation":[4,33,67],"of":[5,56,90,175],"remote":[6,36,91],"sensing":[7,37,92],"images":[8],"arise":[9],"primarily":[10],"from":[11],"significant":[12],"variations":[13],"target":[15],"sizes,":[16],"diverse":[17],"shapes,":[18],"and":[19,76,86,117,161,173],"complex":[20],"background":[21],"environments.":[22],"To":[23],"address":[24],"these":[25,140],"challenges,":[26],"we":[27],"have":[28],"developed":[29],"a":[30,65,107,131],"feature-guided":[31],"model":[34,68,150],"for":[35],"images,":[38],"further":[39,138],"enhancing":[40],"its":[41],"accuracy":[42],"with":[43],"high-fidelity":[44],"masks":[45],"generated":[46],"by":[47],"the":[48,83,87,101,146,149,153,162,171,176],"SAM":[49,102],"vision":[50,103],"large":[51,104],"model.":[52],"principal":[54],"contributions":[55],"this":[57],"study":[58],"are":[59],"outlined":[60],"as":[61],"follows:":[62],"We":[63,94],"introduce":[64],"that":[69,110],"employs":[70],"feature":[71],"guidance,":[72],"ingeniously":[73],"integrating":[74],"CNN":[75],"Transformer":[77],"architectures":[78],"to":[79,137,159,168],"effectively":[80],"capture":[81],"both":[82,128],"local":[84],"details":[85],"global":[88],"context":[89],"images.":[93],"propose":[95],"an":[96],"improved":[97,152],"method":[98],"based":[99],"on":[100],"model,":[105],"featuring":[106],"dual-branch":[108],"structure":[109],"incorporates":[111],"two":[112],"key":[113],"modules:":[114],"voting":[116,122],"mask":[118,132],"refinement.":[119],"module":[123,134],"corrects":[124],"errors":[126],"branches.":[129],"Subsequently,":[130],"refinement":[133],"is":[135],"utilized":[136],"enhance":[139],"masks.":[141],"In":[142],"experimental":[143],"validations":[144],"using":[145],"iSAID":[147],"dataset,":[148],"significantly":[151],"mean":[154,163],"Intersection":[155],"over":[156],"Union":[157],"(mIoU)":[158],"61.54%":[160],"<italic":[164],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">F</i>1":[166],"score":[167],"74.69%,":[169],"underscoring":[170],"significance":[172],"applicability":[174],"proposed":[177],"methodology.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}