2024/03/07 by Akansh Maurya, Maurya, Akansh, Hewan Shrestha +3
Earth and Planetary Sciences · Computer Science · #Geological Modeling and Analysis #Geochemistry and Geologic Mapping
paper · pdf · doi:10.48550/arxiv.2403.04859
With the limited availability of labeled data with various atmospheric conditions in remote sensing images, it seems useful to work with self-supervised algorithms. Few pretext-based algorithms, including from rotation, spatial context and jigsaw puzzles are not appropriate for satellite images. Often, satellite images have a higher temporal frequency. So, the temporal dimension of remote sensing data provides natural augmentation without requiring us to create artificial augmentation of images. Here, we propose S3-TSS, a novel method of self-supervised learning technique that leverages natural augmentation occurring in temporal dimension. We compare our results with current state-of-the-art methods and also perform various experiments. We observed that our method was able to perform better than baseline SeCo in four downstream datasets. Code for our work can be found here: https://github.com/hewanshrestha/Why-Self-Supervision-in-Time