InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization

TL;DR

InfoGeo introduces an information-theoretic object-centric learning framework to improve cross-view UAV geo-localization, enhancing robustness and generalization under diverse conditions.

Contribution

It proposes a novel information bottleneck approach inspired by object-centric learning to address domain shifts in cross-view geo-localization.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Enhances robustness against regional textures and weather variations.

Effectively reduces view-specific noise through cross-view constraints.

Abstract

Cross-view geo-localization (CVGL) is fundamental for precise localization and navigation in GPS-denied environments, aiming to match ground or UAV imagery with satellite views. Existing approaches often rely on global feature alignment, but they suffer from substantial domain shifts induced by varying regional textures and weather conditions. This issue becomes even more pronounced in UAV-based scenarios, where the broader perspective inevitably introduces dense, fine-grained objects, creating significant visual clutter. To address this, we draw inspiration from Object-Centric Learning (OCL) and propose InfoGeo, an information-theoretic framework designed to enhance robustness and generalization. InfoGeo reformulates the optimization as an information bottleneck process with two core objectives: (i) maximizing view-invariant information by aligning the object-centric structural relations across views, and (ii) minimizing view-specific noisy signals through cross-view knowledge constraints. Extensive evaluations across diverse benchmarks and challenging scenarios demonstrate that InfoGeo significantly outperforms state-of-the-art methods.