{"id":"https://openalex.org/W4416251444","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228553","title":"RSDiX: Lightweight and Data-Efficient VLMs for Remote Sensing through Self-Distillation","display_name":"RSDiX: Lightweight and Data-Efficient VLMs for Remote Sensing through Self-Distillation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251444","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228553"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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":"https://openalex.org/A5103135525","display_name":"Andrea Terlizzi","orcid":"https://orcid.org/0000-0002-4963-8596"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Andrea Terlizzi","raw_affiliation_strings":["University of Salerno,NeuroneLab DISA-MIS,Italy,8404"],"affiliations":[{"raw_affiliation_string":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120354532","display_name":"Angelo Nazzaro","orcid":null},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Angelo Nazzaro","raw_affiliation_strings":["University of Salerno,NeuroneLab DISA-MIS,Italy,8404"],"affiliations":[{"raw_affiliation_string":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120450583","display_name":"Lorenzo Bernardi","orcid":null},"institutions":[{"id":"https://openalex.org/I90435624","display_name":"TXT e-solutions (Italy)","ror":"https://ror.org/01h89k731","country_code":"IT","type":"company","lineage":["https://openalex.org/I90435624"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Bernardi","raw_affiliation_strings":["NAIS Solutions,Rome,Italy,00183"],"affiliations":[{"raw_affiliation_string":"NAIS Solutions,Rome,Italy,00183","institution_ids":["https://openalex.org/I90435624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057927455","display_name":"Francesco Bardozzo","orcid":"https://orcid.org/0000-0003-0199-6623"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Bardozzo","raw_affiliation_strings":["University of Salerno,NeuroneLab DISA-MIS,Italy,8404"],"affiliations":[{"raw_affiliation_string":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030668200","display_name":"Roberto Tagliaferri","orcid":"https://orcid.org/0000-0001-8134-9025"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Tagliaferri","raw_affiliation_strings":["University of Salerno,NeuroneLab DISA-MIS,Italy,8404"],"affiliations":[{"raw_affiliation_string":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404","institution_ids":["https://openalex.org/I131729948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103135525"],"corresponding_institution_ids":["https://openalex.org/I131729948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37457952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7394999861717224,"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":0.7394999861717224,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.04919999837875366,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0340999998152256,"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/closed-captioning","display_name":"Closed captioning","score":0.9661999940872192},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5199000239372253},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48260000348091125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3953000009059906},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.36160001158714294},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35929998755455017},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9661999940872192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250999927520752},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48260000348091125},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3984000086784363},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1958291604","https://openalex.org/W1980038761","https://openalex.org/W2020912318","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2294802479","https://openalex.org/W2466055095","https://openalex.org/W2506483933","https://openalex.org/W2515866431","https://openalex.org/W2564590796","https://openalex.org/W2592962403","https://openalex.org/W2626107033","https://openalex.org/W2779054585","https://openalex.org/W2890732922","https://openalex.org/W2901458284","https://openalex.org/W2964343359","https://openalex.org/W2970641574","https://openalex.org/W2979924880","https://openalex.org/W3011916860","https://openalex.org/W3012326541","https://openalex.org/W3046260628","https://openalex.org/W3091842132","https://openalex.org/W3154766321","https://openalex.org/W3165084071","https://openalex.org/W3175955584","https://openalex.org/W3194015448","https://openalex.org/W4206111836","https://openalex.org/W4211112734","https://openalex.org/W4241824578","https://openalex.org/W4292968451","https://openalex.org/W4312389717","https://openalex.org/W4353015365","https://openalex.org/W4387402974","https://openalex.org/W4390873312","https://openalex.org/W4393159564","https://openalex.org/W4394938913","https://openalex.org/W4399399400","https://openalex.org/W4404783209"],"related_works":[],"abstract_inverted_index":{"Remote":[0],"sensing":[1],"(RS)":[2],"imagery":[3],"plays":[4],"a":[5,28,53,61,111,132],"pivotal":[6],"role":[7],"in":[8,36,196],"various":[9,75],"applications,":[10],"and":[11,40,78,88,103,121,147],"recent":[12],"deep":[13,183],"learning":[14,106,128,184],"models":[15,65,185],"integrate":[16],"nuanced":[17],"linguistic":[18],"information":[19],"to":[20,177,179],"enhance":[21],"semantic":[22,170],"understanding.":[23],"This":[24],"work":[25],"introduces":[26],"RSDiX-CLIP,":[27],"fine-tuned":[29],"CLIP":[30],"model":[31,76,113],"that":[32,59],"addresses":[33],"intra-class":[34],"similarity":[35],"RS":[37,71,81,134,187],"image":[38,72,82],"datasets":[39],"improves":[41],"data":[42],"efficiency":[43],"through":[44],"the":[45,56,97,115,119,125,159,166,180,197],"OTTER":[46],"self-distillation":[47],"framework.":[48,129],"Additionally,":[49],"we":[50,151],"propose":[51],"RSDiX-CLIPCap,":[52],"variant":[54],"of":[55,99,114,139,169,182],"CLIPCap":[57],"framework":[58],"incorporates":[60],"pre-trained":[62],"RSDiX-CLIP.":[63],"Our":[64],"outperform":[66],"state-of-the-art":[67],"methods":[68],"on":[69,124],"zero-shot":[70],"classification":[73],"at":[74,202],"scales":[77],"attain":[79],"competitive":[80],"captioning":[83,135,155],"results,":[84],"while":[85],"being":[86],"smaller":[87],"more":[89],"data-efficient":[90],"than":[91],"existing":[92],"methods.":[93],"We":[94,130],"also":[95],"explore":[96],"impact":[98],"mixed":[100],"distillation":[101],"strategies":[102],"alternative":[104],"contrastive":[105,127],"frameworks,":[107],"introducing":[108],"RSDiX-CLIP-S-BERT,":[109],"employing":[110],"text-only":[112],"Sentence-BERT":[116],"family":[117],"as":[118,158],"teacher,":[120],"RSDiX-SigLIP,":[122],"built":[123],"SigLIP":[126],"present":[131],"novel":[133],"dataset,":[136],"S2LCD,":[137],"consisting":[138],"1533":[140],"Sentinel-2":[141],"images":[142],"with":[143],"7665":[144],"wide-vocabulary,":[145],"diverse":[146],"detailed":[148],"captions.":[149],"Finally,":[150],"challenge":[152],"traditional":[153],"N-gram-based":[154],"metrics":[156],"such":[157],"BLEU":[160],"score,":[161],"providing":[162],"statistical":[163],"evidence":[164],"for":[165,186,193],"higher":[167],"effectiveness":[168],"scores":[171],"like":[172],"Sentence-BERT-Similarity.":[173],"These":[174],"advancements":[175],"aim":[176],"contribute":[178],"data-efficiency":[181],"image-text":[188],"tasks,":[189],"offering":[190],"promising":[191],"avenues":[192],"further":[194],"exploration":[195],"field.":[198],"Code":[199],"&":[200],"Data":[201],"https://github.com/NeuRoNeLab/RSDiX-CLIP.":[203]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}