Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery

TL;DR

This paper introduces GeoRank, a regularization method for contrastive self-supervised learning that leverages geographical information to enhance feature embedding in multispectral remote sensing images, outperforming existing methods.

Contribution

The paper proposes GeoRank, a novel regularization technique that incorporates geographical relationships into contrastive SSL for remote sensing, and systematically studies key adaptations for multispectral data.

Findings

GeoRank improves contrastive SSL performance on remote sensing data.

Incorporating geographical information enhances feature embedding quality.

The effectiveness of data augmentations and dataset size varies with task and data characteristics.

Abstract

Self-supervised learning (SSL) has become a powerful paradigm for learning from large, unlabeled datasets, particularly in computer vision (CV). However, applying SSL to multispectral remote sensing (RS) images presents unique challenges and opportunities due to the geographical and temporal variability of the data. In this paper, we introduce GeoRank, a novel regularization method for contrastive SSL that improves upon prior techniques by directly optimizing spherical distances to embed geographical relationships into the learned feature space. GeoRank outperforms or matches prior methods that integrate geographical metadata and consistently improves diverse contrastive SSL algorithms (e.g., BYOL, DINO). Beyond this, we present a systematic investigation of key adaptations of contrastive SSL for multispectral RS images, including the effectiveness of data augmentations, the impact of dataset cardinality and image size on performance, and the task dependency of temporal views. Code is available at https://github.com/tomburgert/georank.