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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xiao, Jiuhong, Zhu, Gao, Loianno, Giuseppe
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912128180420608
author Xiao, Jiuhong
Zhu, Gao
Loianno, Giuseppe
author_facet Xiao, Jiuhong
Zhu, Gao
Loianno, Giuseppe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_00090
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localization
Xiao, Jiuhong
Zhu, Gao
Loianno, Giuseppe
Computer Vision and Pattern Recognition
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.
title VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.00090