{"id":"https://openalex.org/W7165127974","doi":"https://doi.org/10.1109/tip.2026.3702423","title":"LiteMFT: Lightweight Multi-Modal Fine-Tuning for Semantic Segmentation","display_name":"LiteMFT: Lightweight Multi-Modal Fine-Tuning for Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7165127974","doi":"https://doi.org/10.1109/tip.2026.3702423","pmid":"https://pubmed.ncbi.nlm.nih.gov/42313582"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3702423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3702423","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/A5070332131","display_name":"Chaobin Guo","orcid":"https://orcid.org/0009-0009-1276-5936"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwang Guo","raw_affiliation_strings":["School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1276-5936","affiliations":[{"raw_affiliation_string":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054256790","display_name":"Yuxiang Zhang","orcid":"https://orcid.org/0000-0002-2913-3515"},"institutions":[{"id":"https://openalex.org/I4210100650","display_name":"Hong Kong Jockey Club","ror":"https://ror.org/015ygrv52","country_code":"HK","type":"nonprofit","lineage":["https://openalex.org/I4210100650"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxiang Zhang","raw_affiliation_strings":["Department of Geography, Jockey Club STEM Laboratory of Quantitative Remote Sensing, The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Geography, Jockey Club STEM Laboratory of Quantitative Remote Sensing, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I4210100650","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442192","display_name":"Mengmeng Zhang","orcid":"https://orcid.org/0000-0002-5724-9785"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng Zhang","raw_affiliation_strings":["School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5724-9785","affiliations":[{"raw_affiliation_string":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339065","display_name":"Huan Liu","orcid":"https://orcid.org/0000-0003-4642-4485"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Liu","raw_affiliation_strings":["School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4642-4485","affiliations":[{"raw_affiliation_string":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100317994","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7015-7335"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7015-7335","affiliations":[{"raw_affiliation_string":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.6770481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"6674","last_page":"6685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5234000086784363,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5234000086784363,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.20260000228881836,"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/T10028","display_name":"Topic Modeling","score":0.12330000102519989,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5652999877929688},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5098000168800354},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.42640000581741333},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.40689998865127563},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3257000148296356},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2851000130176544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245000004768372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621999979019165},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5652999877929688},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5291000008583069},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.42640000581741333},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.40689998865127563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2705000042915344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.25279998779296875},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3702423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3702423","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:42313582","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42313582","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":[],"awards":[{"id":"https://openalex.org/G234700108","display_name":null,"funder_award_id":"62471040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5136031712","display_name":null,"funder_award_id":"62301044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5768393872","display_name":null,"funder_award_id":"W2411055","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":55,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W2066813062","https://openalex.org/W2136251662","https://openalex.org/W2152057649","https://openalex.org/W2560023338","https://openalex.org/W2587989515","https://openalex.org/W2614256707","https://openalex.org/W2765739551","https://openalex.org/W2770233088","https://openalex.org/W2774839435","https://openalex.org/W2775906317","https://openalex.org/W2921749009","https://openalex.org/W2956887593","https://openalex.org/W2960933010","https://openalex.org/W3042173136","https://openalex.org/W3091001089","https://openalex.org/W3093327960","https://openalex.org/W3108601100","https://openalex.org/W3110089052","https://openalex.org/W3129601843","https://openalex.org/W3133524663","https://openalex.org/W3170885821","https://openalex.org/W3194841206","https://openalex.org/W3204731106","https://openalex.org/W4200556575","https://openalex.org/W4200635035","https://openalex.org/W4225487034","https://openalex.org/W4226086539","https://openalex.org/W4280490589","https://openalex.org/W4282842343","https://openalex.org/W4294643358","https://openalex.org/W4296913506","https://openalex.org/W4298326888","https://openalex.org/W4312235312","https://openalex.org/W4312651322","https://openalex.org/W4312685069","https://openalex.org/W4313142416","https://openalex.org/W4313156423","https://openalex.org/W4386065698","https://openalex.org/W4386179772","https://openalex.org/W4390489106","https://openalex.org/W4390874575","https://openalex.org/W4393156115","https://openalex.org/W4394938945","https://openalex.org/W4398224523","https://openalex.org/W4402716193","https://openalex.org/W4402727160","https://openalex.org/W4402727589","https://openalex.org/W4402727771","https://openalex.org/W4406572793","https://openalex.org/W4406949235","https://openalex.org/W4409366900","https://openalex.org/W4413155942","https://openalex.org/W7160106647"],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0,69],"image":[1,105],"segmentation":[2,155],"has":[3],"recently":[4],"attracted":[5],"considerable":[6],"attention":[7],"due":[8],"to":[9,12,38,82,102,141],"its":[10,176],"ability":[11],"integrate":[13],"complementary":[14,126],"information":[15],"from":[16],"diverse":[17],"sensors,":[18],"thereby":[19],"enabling":[20],"more":[21],"accurate":[22],"semantic":[23,84,183],"predictions":[24],"in":[25,46,181],"complex":[26],"or":[27,164],"specialized":[28],"scenarios.":[29],"However,":[30],"as":[31],"data":[32,143],"volume":[33],"and":[34,48,76,123,130,153,178],"model":[35],"capacity":[36],"continue":[37],"grow,":[39],"many":[40],"existing":[41,100],"methods":[42],"suffer":[43],"substantial":[44],"increases":[45],"parameters":[47],"computational":[49],"costs,":[50],"particularly":[51],"with":[52],"the":[53,115,131,138],"widespread":[54],"adoption":[55],"of":[56,79,92,99],"Vision":[57],"Foundation":[58],"Models":[59],"(VFMs).":[60],"To":[61],"address":[62],"these":[63],"challenges,":[64],"we":[65],"introduce":[66],"a":[67,89],"Lightweight":[68],"Fine-Tuning":[70],"framework":[71,109],"(LiteMFT)":[72],"designed":[73],"for":[74,172],"efficient":[75],"generalizable":[77],"adaptation":[78],"RGB-pretrained":[80],"VFMs":[81],"multi-modal":[83,104,142,182],"segmentation.":[85,184],"By":[86],"incorporating":[87],"only":[88,161],"small":[90],"number":[91],"trainable":[93],"parameters,":[94],"LiteMFT":[95,159],"enables":[96],"effective":[97],"extension":[98],"models":[101],"handle":[103],"fusion":[106],"tasks.":[107],"The":[108],"centers":[110],"around":[111],"two":[112],"key":[113],"components:":[114],"Modality":[116],"Local":[117],"Competition":[118],"(MLC)":[119],"module,":[120],"which":[121,136],"dynamically":[122],"efficiently":[124],"fuses":[125],"features":[127],"across":[128],"modalities,":[129,174],"Gated":[132],"Low-Rank":[133],"Adapter":[134],"(GLR),":[135],"improves":[137],"backbone's":[139],"adaptability":[140],"through":[144],"content-aware":[145],"low-rank":[146],"transformation.":[147],"Extensive":[148],"experiments":[149],"on":[150],"both":[151],"bi-modal":[152],"tri-modal":[154],"tasks":[156],"demonstrate":[157],"that":[158],"not":[160],"achieves":[162],"competitive":[163],"superior":[165],"performance":[166],"but":[167],"also":[168],"exhibits":[169],"strong":[170],"scalability":[171],"additional":[173],"underscoring":[175],"practicality":[177],"broad":[179],"applicability":[180]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2026-06-19T00:00:00"}