{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:33Z","timestamp":1763191953055,"version":"3.45.0"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228553","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["RSDiX: Lightweight and Data-Efficient VLMs for Remote Sensing through Self-Distillation"],"prefix":"10.1109","author":[{"given":"Andrea","family":"Terlizzi","sequence":"first","affiliation":[{"name":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404"}]},{"given":"Angelo","family":"Nazzaro","sequence":"additional","affiliation":[{"name":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404"}]},{"given":"Lorenzo","family":"Bernardi","sequence":"additional","affiliation":[{"name":"NAIS Solutions,Rome,Italy,00183"}]},{"given":"Francesco","family":"Bardozzo","sequence":"additional","affiliation":[{"name":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404"}]},{"given":"Roberto","family":"Tagliaferri","sequence":"additional","affiliation":[{"name":"University of Salerno,NeuroneLab DISA-MIS,Italy,8404"}]}],"member":"263","reference":[{"article-title":"Rs5m: A large scale vision-language dataset for remote sensing vision-language foundation model","year":"2023","author":"Zhang","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3390838"},{"key":"ref6","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"article-title":"The llama 3 herd of models","year":"2024","author":"Dubey","key":"ref7"},{"article-title":"Geollava: Efficient fine-tuned vision-language models for temporal change detection in remote sensing","year":"2024","author":"Elgendy","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04393-x"},{"article-title":"Data efficient language-supervised zero-shot recognition with optimal transport distillation","year":"2021","author":"Wu","key":"ref11"},{"article-title":"Clipcap: Clip prefix for image captioning","year":"2021","author":"Mokady","key":"ref12"},{"key":"ref13","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103497"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224244"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"article-title":"Sinkhorn distances: Lightspeed computation of optimal transportation distances","year":"2013","author":"Cuturi","key":"ref23"},{"article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","year":"2020","author":"Wang","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Practical bayesian optimization of machine learning algorithms","year":"2012","author":"Snoek","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4020"},{"article-title":"Decoupled weight decay regularization","year":"2019","author":"Loshchilov","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8519248"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.10.035004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.09.020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/s20061594"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2496185"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2010.2055033"},{"key":"ref40","article-title":"Structural high-resolution satellite image indexing","author":"Xia","year":"2010","journal-title":"Advancing Remote Sensing Science"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2475299"},{"article-title":"Training compute-optimal large language models","year":"2022","author":"Hoffmann","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010106"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref52","article-title":"Description generation for remote sensing images using attribute attention mechanism","volume-title":"Remote Sensing","author":"Zhang","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.797"},{"key":"ref54","article-title":"Data management for large language models: A survey","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/e17-1019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.566"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199842193.013.001"},{"article-title":"Coca: Contrastive captioners are image-text foundation models","year":"2022","author":"Yu","key":"ref58"},{"article-title":"Phi-3 technical report: A highly capable language model locally on your phone, 2024","year":"2024","author":"Abdin","key":"ref59"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228553.pdf?arnumber=11228553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:27:32Z","timestamp":1763191652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228553","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}