{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:53:04Z","timestamp":1782834784028,"version":"3.54.5"},"reference-count":238,"publisher":"Tsinghua University Press","issue":"5","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62495061,62495064,62476143"],"award-info":[{"award-number":["62495061,62495064,62476143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.26599\/cvm.2025.9450490","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:59:22Z","timestamp":1754503162000},"page":"897-937","source":"Crossref","is-referenced-by-count":6,"title":["Remote Sensing Tuning: A Survey"],"prefix":"10.26599","volume":"11","author":[{"given":"Dongshuo","family":"Yin","sequence":"first","affiliation":[{"name":"Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting-Feng","family":"Zhao","sequence":"additional","affiliation":[{"name":"TKLNDST, College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deng-Ping","family":"Fan","sequence":"additional","affiliation":[{"name":"TKLNDST, College of Computer Science, Nankai University,Tianjin,China,300350"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shutao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University,Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province,Changsha,China,410082"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Wuhan University,Hubei Key Laboratory of Multimedia and Network Communication Engineering,Wuhan,China,430072"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","article-title":"Vision foundation models in remote sensing: A survey","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2025.3576766"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03608-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.4236\/jgis.2022.141001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/agj2.20595"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2020.100178"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/jmse9040397"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref11","article-title":"Delta tuning: A comprehensive study of parameter efficient methods for pretrained language models","author":"Ding","year":"2022","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3657632"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37136-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs13071243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3052869"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680940"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/10095020.2017.1333230"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2017.2762307"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3351889"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3488731"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3407884"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs15092363"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3532690"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3455427"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3365825"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/app132312857"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3368430"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3368168"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/rs16101742"},{"key":"ref30","article-title":"Efficient remote sensing with harmonized transfer learning and modality alignment","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32912"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3393015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3372416"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3332219"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00281"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3417475"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3422805"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00196"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10641565"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00057"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3509721"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3328981"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359599"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3336283"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3321752"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3461779"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103540"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3449372"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3357777"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"ref53","article-title":"SkySenseGPT: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Learning de-biased representations for remote-sensing imagery","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3470808"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3435745"},{"key":"ref57","article-title":"SSDiff: Spatialspectral integrated diffusion model for remote sensing pansharpening","author":"Zhong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3524578"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3382734"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3411398"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3460085"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2024.2411067"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3430900"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3523505"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/rs15061709"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3390\/su15107854"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.101921"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3390\/s24030770"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.12.004"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/rs17101748"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3443420"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3398038"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref75","article-title":"SatMAE: Pretraining transformers for temporal and multi-spectral satellite imagery","author":"Cong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3557581"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3390\/rs9090907"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8518078"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3390\/rs11242908"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3277588"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3367168"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3390\/rs13193816"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2021.3116858"},{"key":"ref86","article-title":"Rethinking feature backbone fine-tuning for remote sensing object detection","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3312591"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.3390\/rs16122096"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10648191"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00129"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00928"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115569"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00803"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883983"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00148"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3202499"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3204888"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3390\/rs14225675"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3271312"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268232"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00509"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00207"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3316166"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3360447"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_17"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10282433"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3493237"},{"key":"ref116","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref117","article-title":"Foundation models for generalist geospatial artificial intelligence","author":"Jakubik","year":"2023","journal-title":"arXiv preprint"},{"key":"ref118","article-title":"CROMA: Remote sensing representations with contrastive radar-optical masked autoencoders","author":"Fuller","year":"2023","journal-title":"arXiv preprint"},{"key":"ref119","article-title":"USat: A unified self-supervised encoder for multi-sensor satellite imagery","author":"Irvin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref120","article-title":"Cross-scale MAE: A tale of multiscale exploitation in remote sensing","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Tang","year":"2023"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3358066"},{"key":"ref122","article-title":"EarthPT: A time series foundation model for Earth observation","author":"Smith","year":"2024","journal-title":"arXiv preprint"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3354031"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3371481"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3348479"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref127","article-title":"Lightweight, pretrained transformers for remote sensing timeseries","author":"Tseng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02627"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.09.013"},{"key":"ref130","article-title":"FoMo-Bench: A multimodal, multi-scale and multitask Forest Monitoring Benchmark for remote sensing foundation models","author":"Bountos","year":"2024","journal-title":"arXiv preprint"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3382734"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02631"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00251"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10641637"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3401772"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_10"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3769084"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3531988"},{"key":"ref140","article-title":"LeMeViT: Efficient vision transformer with learnable meta tokens for remote sensing image interpretation","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref141","article-title":"Neural plasticity-inspired multimodal foundation model for earth observation","author":"Xiong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref142","article-title":"Parameter-efficient fine-tuning in large models: A survey of methodologies","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00961-0"},{"key":"ref144","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref145","article-title":"Parameter-efficient fine-tuning for pretrained vision models: A survey","author":"Xin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref146","article-title":"Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-9437-9_9"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2024.01.012"},{"key":"ref149","article-title":"Parameter efficient fine tuning: A comprehensive analysis across applications","author":"Balne","year":"2024","journal-title":"arXiv preprint"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref153","article-title":"Parameterefficient transfer learning for NLP","author":"Houlsby","year":"2019","journal-title":"arXiv preprint"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01926"},{"key":"ref155","article-title":"Med-tuning: A new parameter-efficient tuning framework for medical volumetric segmentation","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref157","article-title":"GhostNetv2: Enhance cheap operation with long-range attention","author":"Tang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref160","article-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref161","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref162","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref163","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref165","article-title":"Fast segment anything","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref166","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Fratta","year":"2015","journal-title":"arXiv preprint"},{"key":"ref167","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01869"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref171","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref172","article-title":"Multi LoRA Meets Vision: Merging multiple adapters to create a multi task model","author":"Kesim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1145\/3302506.3310396"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72384-1_26"},{"key":"ref175","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA","author":"Smith","year":"2023","journal-title":"arXiv preprint"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.5194\/isprsannals-i-3-293-2012"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02195"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2858817"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref180","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"arXiv preprint"},{"key":"ref181","article-title":"SPHINX-X: Scaling data and parameters for a family of multimodal large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1117\/12.242059"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref184","article-title":"Frustratingly simple few-shot object detection","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref185","article-title":"InstructionGPT-4: A 200-instruction paradigm for fine-tuning MiniGPT-4","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093471"},{"key":"ref187","article-title":"A remote sensing image dataset for cloud removal","author":"Lin","year":"2019","journal-title":"arXiv preprint"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9884408"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.3390\/rs13245094"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2601622"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.5220\/0006120603240331"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351502"},{"key":"ref199","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref200","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","author":"Zamir","year":"2019","journal-title":"arXiv preprint"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2772-5"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.3390\/rs13245104"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3063797"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.16.014520"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183690"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3170326"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3130174"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090981"},{"key":"ref209","article-title":"MMBench: Is your multimodal model an all-around player","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref211","article-title":"SEED-bench: Benchmarking multimodal LLMs with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3187652"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2947081"},{"key":"ref216","volume-title":"Dstl Satellite Imagery Feature Detection","year":"2016"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.04.014"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2014.2305441"},{"key":"ref219","volume-title":"MUUFL Gulfport hyperspectral and LiDAR airborne data set","author":"Gader","year":"2016"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2020.3017414"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3412112"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.3390\/rs11232844"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1038\/s41893-024-01291-0"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1038\/s41561-023-01323-y"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1016\/j.earscirev.2022.104110"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3121761"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.3390\/rs16234583"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2021.1906985"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.3390\/rs14153674"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.10.001"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02699"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01086"},{"key":"ref233","article-title":"LoRAPrune: Structured pruning meets low-rank parameter-efficient fine-tuning","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref234","article-title":"Memory-efficient fine-tuning of compressed large language models via sub-4-bit integer quantization","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref235","article-title":"BitDelta: Your fine-tune may only be worth one bit","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref236","article-title":"In-context learning distillation for efficient few-shot fine-tuning","author":"Duan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref237","article-title":"Scaling laws for generative mixed-modal language models","author":"Aghajanyan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref238","article-title":"Scaling laws for reward model overoptimization","author":"Gao","year":"2022","journal-title":"arXiv preprint"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11230308\/11119145.pdf?arnumber=11119145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:52:30Z","timestamp":1762455150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11119145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":238,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450490","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}