GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration

TL;DR

GeoExplorer introduces a curiosity-driven exploration approach for active geo-localization, enhancing robustness and generalization in diverse and unseen environments by using intrinsic rewards instead of traditional distance-based methods.

Contribution

The paper presents GeoExplorer, a novel AGL agent that leverages intrinsic curiosity rewards to improve exploration and localization in unseen environments.

Findings

Outperforms existing methods on four benchmarks.

Shows improved robustness in unfamiliar environments.

Demonstrates better generalization to unseen targets.

Abstract

Active Geo-localization (AGL) is the task of localizing a goal, represented in various modalities (e.g., aerial images, ground-level images, or text), within a predefined search area. Current methods approach AGL as a goal-reaching reinforcement learning (RL) problem with a distance-based reward. They localize the goal by implicitly learning to minimize the relative distance from it. However, when distance estimation becomes challenging or when encountering unseen targets and environments, the agent exhibits reduced robustness and generalization ability due to the less reliable exploration strategy learned during training. In this paper, we propose GeoExplorer, an AGL agent that incorporates curiosity-driven exploration through intrinsic rewards. Unlike distance-based rewards, our curiosity-driven reward is goal-agnostic, enabling robust, diverse, and contextually relevant exploration based on effective environment modeling. These capabilities have been proven through extensive experiments across four AGL benchmarks, demonstrating the effectiveness and generalization ability of GeoExplorer in diverse settings, particularly in localizing unfamiliar targets and environments.