Change-Aware Sampling and Contrastive Learning for Satellite Images

Instructions

Part 1: https://zenodo.org/records/10913216

Part 2: https://zenodo.org/records/10914902

Part 3: https://zenodo.org/uploads/10915715

Part 4: https://zenodo.org/records/10916979

cat clean_1m_geography_part* > clean_1m_geography.tar.gz

tar -xvf clean_1m_geography.tar.gz

Paper Abstract

Automatic remote sensing tools can help inform many large-scale challenges such as disaster management, climate change, etc. While a vast amount of spatio-temporal satellite image data is readily available, most of it remains unlabelled. Without labels, this data is not very useful for supervised learning algorithms. Self-supervised learning instead provides a way to learn effective representations for various downstream tasks without labels. In this work, we leverage characteristics unique to satellite images to learn better self-supervised features. Specifically, we use the temporal signal to contrast images with long-term and short-term differences, and we leverage the fact that satellite images do not change frequently. Using these characteristics, we formulate a new loss contrastive loss called Change-Aware Contrastive (CACo) Loss. Further, we also present a novel method of sampling different geographical regions. We show that leveraging these properties leads to better performance on diverse downstream tasks. For example, we see a 6.5% relative improvement for semantic segmentation and an 8.5% relative improvement for change detection over the best-performing baseline with our method.