Exploring Generalisability of Self-Distillation with No Labels for SAR-Based Vegetation Prediction

Published: 28 Oct 2023, Last Modified: 02 Apr 2024DistShift 2023 PosterEveryoneRevisionsBibTeX
Keywords: SAR, SSL, DINO, Vegetation percentage, embeddings
TL;DR: Investigating embedding spaces to predict model generalizability for DINO-ViTs trained on Synthetic Aperature Radar data for downstream vegetation prediction.
Abstract: In this work we pre-train a DINO-ViT based model using two Synthetic Aperture Radar datasets (S1GRD or GSSIC) across three regions (China, Conus, Europe). We fine-tune the models on smaller labeled datasets to predict vegetation percentage, and empirically study the connection between the embedding space of the models and their ability to generalize across diverse geographic regions and to unseen data. For S1GRD, embedding spaces of different regions are clearly separated, while GSSIC's overlaps. Positional patterns remain during fine-tuning, and greater distances in embeddings often result in higher errors for unfamiliar regions. With this, our work increases our understanding of generalizability for self-supervised models applied to remote sensing.
Submission Number: 59