paper-with-me

홈 › Papers

Towards Efficient Benchmarking of Foundation Models in Remote Sensing: A Capabilities Encoding Approach

2025-05-06 · Pierre Adorni, Minh-Tan Pham, Stéphane May, Sébastien Lefèvre

Foundation models constitute a significant advancement in computer vision: after a single, albeit costly, training phase, they can address a wide array of tasks. In the field of Earth observation, over 75 remote sensing vision foundation models have been developed in the past four years. However, none has consistently outperformed the others across all available downstream tasks. To facilitate their comparison, we propose a cost-effective method for predicting a model's performance on multiple downstream tasks without the need for fine-tuning on each one. This method is based on what we call "capabilities encoding." The utility of this novel approach is twofold: we demonstrate its potential to simplify the selection of a foundation model for a given new task, and we employ it to offer a fresh perspective on the existing literature, suggesting avenues for future research. Codes are available at https://github.com/pierreadorni/capabilities-encoding.

📄 PDF Abstract BibTeX arXiv:2505.03299

Code (1)

pierreadorni/capabilities-encoding 공식 구현 jax

Tasks

BenchmarkingEarth Observation

Similar Papers 제목 키워드 기반

RSRefSeg: Referring Remote Sensing Image Segmentation with Foundation Models

2025-01-12 · Keyan Chen, Jiafan Zhang, Chenyang Liu, Zhengxia Zou 외

Referring remote sensing image segmentation is crucial for achieving fine-grained visual understanding through free-format textual input, enabling enhanced scene and object extraction in remote sensing applications. Curr…

Image SegmentationSegmentationSemantic Segmentation

Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing

2026-03-13 · Shuchang Lyu, Haiquan Wen, Guangliang Cheng, Meng Li 외 arxiv

Recent advances in reasoning language models and reinforcement learning with verifiable rewards have significantly enhanced multi-step reasoning capabilities. This progress motivates the extension of reasoning paradigms …

Reinforcement LearningVisual Grounding

DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding

2025-03-20 · Keyan Chen, Chenyang Liu, Bowen Chen, Wenyuan Li 외

The advancement of remote sensing technology has improved the spatial resolution of satellite imagery, facilitating more detailed visual representations for diverse interpretations. However, existing methods exhibit limi…

GPU

CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models

2024-11-27 · Xiao An, Jiaxing Sun, Zihan Gui, wei he

The rapid advancement of Large Vision-Language Models (VLMs), both general-domain models and those specifically tailored for remote sensing, has demonstrated exceptional perception and reasoning capabilities in Earth obs…

BenchmarkingEarth ObservationMultiple-choice

Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook

2025-05-01 · Muyi Bao, Shuchang Lyu, Zhaoyang Xu, Huiyu Zhou 외

Deep learning has profoundly transformed remote sensing, yet prevailing architectures like Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) remain constrained by critical trade-offs: CNNs suffer from l…

BenchmarkingChange DetectionMambaSemantic Segmentation+1