paper-with-me

홈 › Papers

SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models

2023-04-23 · Jonathan Roberts, Kai Han, Samuel Albanie

Interpreting remote sensing imagery enables numerous downstream applications ranging from land-use planning to deforestation monitoring. Robustly classifying this data is challenging due to the Earth's geographic diversity. While many distinct satellite and aerial image classification datasets exist, there is yet to be a benchmark curated that suitably covers this diversity. In this work, we introduce SATellite ImageNet (SATIN), a metadataset curated from 27 existing remotely sensed datasets, and comprehensively evaluate the zero-shot transfer classification capabilities of a broad range of vision-language (VL) models on SATIN. We find SATIN to be a challenging benchmark-the strongest method we evaluate achieves a classification accuracy of 52.0%. We provide a $\href{https://satinbenchmark.github.io}{\text{public leaderboard}}$ to guide and track the progress of VL models in this important domain.

📄 PDF Abstract BibTeX arXiv:2304.11619

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationDiversityimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Hyperparameter Tuning MLPs for Probabilistic Time Series Forecasting

2024-03-07 · Kiran Madhusudhanan, Shayan Jawed, Lars Schmidt-Thieme

Time series forecasting attempts to predict future events by analyzing past trends and patterns. Although well researched, certain critical aspects pertaining to the use of deep learning in time series forecasting remain…

Hyperparameter OptimizationProbabilistic Time Series ForecastingTime SeriesTime Series Forecasting

Deep Blind Super-Resolution for Satellite Video

2024-01-13 · Yi Xiao, Qiangqiang Yuan, Qiang Zhang, Liangpei Zhang

Recent efforts have witnessed remarkable progress in Satellite Video Super-Resolution (SVSR). However, most SVSR methods usually assume the degradation is fixed and known, e.g., bicubic downsampling, which makes them vul…

Blind Super-ResolutionSuper-ResolutionVideo Super-Resolution

FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networks

2023-11-02 · Zheng Lin, Zhe Chen, Zihan Fang, Xianhao Chen 외

Recently, a large number of Low Earth Orbit (LEO) satellites have been launched and deployed successfully in space by commercial companies, such as SpaceX. Due to multimodal sensors equipped by the LEO satellites, they s…

Federated Learningimage-classificationImage ClassificationRemote Sensing Image Classification

Classifying point clouds at the facade-level using geometric features and deep learning networks

2024-02-09 · Yue Tan, Olaf Wysocki, Ludwig Hoegner, Uwe Stilla

3D building models with facade details are playing an important role in many applications now. Classifying point clouds at facade-level is key to create such digital replicas of the real world. However, few studies have …

ClassificationDeep LearningPoint Cloud ClassificationSemantic Segmentation

Satellite image classification with neural quantum kernels

2024-09-30 · Pablo Rodriguez-Grasa, Robert Farzan-Rodriguez, Gabriele Novelli, Yue Ban 외

Achieving practical applications of quantum machine learning for real-world scenarios remains challenging despite significant theoretical progress. This paper proposes a novel approach for classifying satellite images, a…

ClassificationEarth Observationimage-classificationImage Classification+2