Related papers: One for All: Toward Unified Foundation Models for …
Earth observation (EO) in open-world settings presents a unique challenge: different applications rely on diverse sensor modalities, each with varying ground sampling distances, spectral ranges, and numbers of spectral bands. However,…
The foundation model is not the last chapter of the model production pipeline. Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of the foundation model's application. In this paper, we…
We aim to develop a robust yet flexible visual foundation model for Earth observation. It should possess strong capabilities in recognizing and localizing diverse visual targets while providing compatibility with various input-output…
We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design or use neural architecture search (NAS) to find a specialized…
Foundation models are rapidly transforming Earth Observation data mining by enabling generalizable and scalable solutions for key tasks such as scene classification and semantic segmentation. While most efforts in the geospatial domain have…
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…
Foundation models have garnered increasing attention for representation learning in remote sensing. Many such foundation models adopt approaches that have demonstrated success in computer vision with minimal domain-specific modification.…
Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most…
Foundation models refer to deep learning models pretrained on large unlabeled datasets through self-supervised algorithms. In the Earth science and remote sensing communities, there is growing interest in transforming the use of Earth…
Deploying Deep Neural Networks (DNNs) on different hardware platforms is challenging due to varying resource constraints. Besides handcrafted approaches aiming at making deep models hardware-friendly, Neural Architectures Search is rising…
Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO…
Recent progress in self-supervision shows that pre-training large neural networks on vast amounts of unsupervised data can lead to impressive increases in generalisation for downstream tasks. Such models, recently coined as foundation…
Foundation models have the potential to transform the landscape of remote sensing (RS) data analysis by enabling large computer vision models to be pre-trained on vast amounts of remote sensing data. These models can then be fine-tuned with…
Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to substantial increases in generalization to downstream tasks. Such models, recently coined foundation…
The multi-modal remote sensing foundation model (MM-RSFM) has significantly advanced various Earth observation tasks, such as urban planning, environmental monitoring, and natural disaster management. However, most existing approaches…
Once-for-All (OFA) training enables a single super-net to generate multiple sub-nets tailored to diverse deployment scenarios, supporting flexible trade-offs among accuracy, robustness, and model-size without retraining. However, as the…
Neural Architecture Search has proven an effective method of automating architecture engineering. Recent work in the field has been to look for architectures subject to multiple objectives such as accuracy and latency to efficiently deploy…
Weight-sharing neural architecture search aims to optimize a configurable neural network model (supernet) for a variety of deployment scenarios across many devices with different resource constraints. Existing approaches use evolutionary…
Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints by decoupling the training and the searching stages.…
Forests are vital to ecosystems, supporting biodiversity and essential services, but are rapidly changing due to land use and climate change. Understanding and mitigating negative effects requires parsing data on forests at global scale…