ReLATE: Reliability-Guided Evidence Fusion for Robust UAV--Satellite cross-view Geo-Localization

2026-07-28

AI Summary

Existing drone-to-satellite cross-view geolocalization methods suffer from insufficient robustness under real-world image degradations such as adverse weather, illumination variations, and motion blur. To address this limitation, this work introduces UAVSat-Deg, a large-scale benchmark for evaluating degradation robustness, and proposes ReLATE—a novel framework that enables the first systematic assessment of cross-view localization performance under diverse degradation conditions. ReLATE incorporates a reliability-guided evidence fusion mechanism, leveraging a structurally smoothed reliability field to adaptively modulate visual tokens. It further integrates reliability estimation, local evidence aggregation, and a fusion strategy combining CLS-token and GeM pooling branches. Experiments demonstrate that ReLATE significantly outperforms existing methods on UAVSat-Deg, achieving state-of-the-art average performance across various degradations while maintaining high accuracy on clean images.

Abstract

Unmanned aerial vehicle (UAV)-satellite cross-view geo-localization matches UAV images against satellite imagery and has achieved impressive accuracy on clean (non-degraded) image benchmarks. In real-world flights, however, UAV observations are frequently affected by adverse weather, illumination changes, platform motion, sensor noise, and compression, while the robustness of existing methods under such degradations remains largely unexamined. In this paper, we present UAVSat-Deg, a large-scale robustness benchmark for degraded UAV-satellite geo-localization, comprising University-1652-Deg and SUES-200-Deg. UAVSat-Deg covers 27 corruption types, including 19 core and 8 compound corruptions, at three severity levels, supports bidirectional drone-to-satellite and satellite-to-drone retrieval as well as multi-height UAV acquisition, and contains more than 11.7 million pre-generated corrupted test images. Benchmarking representative methods under this protocol reveals substantial robustness gaps, particularly under severe and compound corruptions. To address this problem, we propose ReLATE, a Reliable Evidence Learning framework with Adaptive Token Evidence Regulation, which realizes reliability-adaptive feature fusion during descriptor construction. ReLATE estimates a structure-smoothed reliability field over visual tokens, aggregates trustworthy local evidence, and adaptively integrates it into query-derived representations; the regulated query representations are then combined with the CLS-token and GeM-pooled branches to form the final cross-view descriptor. Across both test sets and retrieval directions, ReLATE achieves the best average corrupted-test performance among the compared methods while maintaining competitive accuracy on clean images. The code and dataset will be available at https://github.com/JHC626/ReLATE.

Problem

• UAV-satellite geo-localization
• image degradation
• robustness
• cross-view matching
• adverse conditions

Innovation

• reliability-guided fusion
• cross-view geo-localization
• robustness benchmark
• adaptive token regulation
• UAV-satellite matching