Using satellite imagery to understand and promote sustainable development

M Burke, A Driscoll, DB Lobell, S Ermon - Science, 2021 - science.org
BACKGROUND Accurate and comprehensive measurements of a range of sustainable
development outcomes are fundamental inputs into both research and policy. For instance …

Satmae: Pre-training transformers for temporal and multi-spectral satellite imagery

Y Cong, S Khanna, C Meng, P Liu… - Advances in …, 2022 - proceedings.neurips.cc
Unsupervised pre-training methods for large vision models have shown to enhance
performance on downstream supervised tasks. Develo** similar techniques for satellite …

Geography-aware self-supervised learning

K Ayush, B Uzkent, C Meng… - Proceedings of the …, 2021 - openaccess.thecvf.com
Contrastive learning methods have significantly narrowed the gap between supervised and
unsupervised learning on computer vision tasks. In this paper, we explore their application …

Domino: Discovering systematic errors with cross-modal embeddings

S Eyuboglu, M Varma, K Saab, JB Delbrouck… - ar** from high resolution remote sensing images
K Ayush, B Uzkent, K Tanmay, M Burke… - Proceedings of the …, 2021 - ojs.aaai.org
The combination of high-resolution satellite imagery and machine learning have proven
useful in many sustainability-related tasks, including poverty prediction, infrastructure …

Urbanclip: Learning text-enhanced urban region profiling with contrastive language-image pretraining from the web

Y Yan, H Wen, S Zhong, W Chen, H Chen… - Proceedings of the …, 2024 - dl.acm.org
Urban region profiling from web-sourced data is of utmost importance for urban computing.
We are witnessing a blossom of LLMs for various fields, especially in multi-modal data …

Contrastive multiview coding with electro-optics for SAR semantic segmentation

K Cha, J Seo, Y Choi - IEEE Geoscience and Remote Sensing …, 2021 - ieeexplore.ieee.org
In the training of deep learning models, how the model parameters are initialized greatly
affects the model performance, sample efficiency, and convergence speed. Recently …