2 papers
cs.CV2026
GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representations
Zeping Liu, Ni Lao, Zhangyu Wang +2
Vision Transformer (ViT) has been widely used in computer vision tasks with excellent results by providing representations for a whole image or image patches. However, ViT lacks de…
cs.CV2025
Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms
Boyi Chen, Zhangyu Wang, Fabian Deuser +2
Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in m…