VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localization

TL;DR

This paper introduces VG-SSL, a benchmarking framework for self-supervised learning in visual geo-localization, demonstrating that contrastive and information maximization methods can match or outperform supervised approaches.

Contribution

It presents the first benchmarking study of SSL methods in visual geo-localization, with a novel geo-related pair strategy and extensive performance analysis.

Findings

Contrastive learning improves geo-specific representations.

Information maximization methods perform well in VG tasks.

SSL methods can match or surpass state-of-the-art VG techniques.

Abstract

Visual Geo-localization (VG) is a critical research area for identifying geo-locations from visual inputs, particularly in autonomous navigation for robotics and vehicles. Current VG methods often learn feature extractors from geo-labeled images to create dense, geographically relevant representations. Recent advances in Self-Supervised Learning (SSL) have demonstrated its capability to achieve performance on par with supervised techniques with unlabeled images. This study presents a novel VG-SSL framework, designed for versatile integration and benchmarking of diverse SSL methods for representation learning in VG, featuring a unique geo-related pair strategy, GeoPair. Through extensive performance analysis, we adapt SSL techniques to improve VG on datasets from hand-held and car-mounted cameras used in robotics and autonomous vehicles. Our results show that contrastive learning and information maximization methods yield superior geo-specific representation quality, matching or surpassing the performance of state-of-the-art VG techniques. To our knowledge, This is the first benchmarking study of SSL in VG, highlighting its potential in enhancing geo-specific visual representations for robotics and autonomous vehicles. The code is publicly available at https://github.com/arplaboratory/VG-SSL.