Change-Aware Sampling and Contrastive Learning for Satellite Images (original) (raw)
Utkarsh Mall, Bharath Hariharan, Kavita Bala
Cornell University
In CVPR 2023
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.
Video
An 8-minute presentation of our work.
Paper
[pdf] [supplementary pdf]
Utkarsh Mall, Bharath Hariharan and Kavita Bala. "Change-Aware Sampling and Contrastive Learning for Satellite Images". In CVPR, 2023.
` @inproceedings{caco-23,
title={Change-Aware Sampling and Contrastive Learning for Satellite Images},
author={Mall, Utkarsh and Hariharan, Bharath and Bala, Kavita},
booktitle={CVPR},
year={2023}
}
`
Poster
