Self-Supervision, Remote Sensing and Abstraction: Representation Learning Across 3 Million Locations

Abstract

Self-supervision based deep learning classification approaches have received considerable attention in academic literature. However, the performance of such methods on remote sensing imagery domains remains under-explored. In this work, we explore contrastive representation learning methods on the task of imagery-based city classification, an important problem in urban computing. We use satellite and map imagery across 2 domains, 3 million locations and more than 1500 cities. We show that self-supervised methods can build a generalizable representation from as few as 200 cities, with representations achieving over 95\% accuracy in unseen cities with minimal additional training. We also find that the performance discrepancy of such methods, when compared to supervised methods, induced by the domain discrepancy between natural imagery and abstract imagery is significant for remote sensing imagery. We compare all analysis against existing supervised models from academic literature and open-source our models for broader usage and further criticism.

Preprint of https://ieeexplore.ieee.org/document/9647061

References in corpus (4)

• Bootstrap your own latent: A new approach to self-supervised Learning
• Identifying safe intersection design through unsupervised feature extraction from satellite imagery
• Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
• The Nature of Human Settlement: Building an understanding of high performance city design