AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration

Li Mi, Manon Béchaz, Zeming Chen, Antoine Bosselut, Devis Tuia

ICCV 2025 · Reinforcement learning › Visual and representation RL · approach: Novelty and impact-driven exploration · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add state modeling loss (action-state dynamics modeling) (ablation)GeoExplorer with extrinsic reward · MasaSuccess ratio: SR improves 0.0277 on averageImproved
add curiosity intrinsic reward without state modeling (ablation)GeoExplorer · MasaSuccess ratio: 0.0357 on averageImproved
add learned state modeling to curiosity reward (ablation)GeoExplorer · MasaSuccess ratio: 0.0507 on averageImproved
use cosine similarity instead of MSE for intrinsic reward (ablation)GeoExplorer · MasaSuccess ratio: average SR difference of 0.0130No clear effect
add intrinsic reward (beta 0 to 0.25) (ablation)GeoExplorer · Masa (C=8)Success ratio: 0.8648 -> 0.9497Improved
raise intrinsic weight beta from 0.25 to 0.5 (ablation)GeoExplorer · Masa (C=4)Success ratio: 0.4324 -> 0.3597Hurt
raise intrinsic weight beta from 0.25 to 1 (ablation)GeoExplorer · Masa (C=8)Success ratio: 0.9497 -> 0.9352Hurt
state modeling loss weight alpha 1 versus action loss only (ablation)GeoExplorer DM stage · Masa action predictionAccuracy: improvement of 0.0271 over alpha=0 (0.3432 -> 0.3703)Improved
add state modeling and curiosity reward on short paths (ablation)GeoExplorer · Masa (C=4)Success ratio: 0.4090 -> 0.3978Hurt
use GeoExplorer instead of GOMAA-Geo (ablation)GOMAA-Geo · MasaSuccess ratio: 0.0234 at C=4 and 0.1643 at C=8Improved
use GeoExplorer instead of GOMAA-Geo for unseen targets (ablation)GOMAA-Geo · SwissViewMonumentsSuccess ratio: 0.1433 (aerial), 0.1366 (ground) at C=6Improved
use GeoExplorer instead of GOMAA-Geo in cross-modal goals (ablation)GOMAA-Geo · MM-GAGSuccess ratio: 0.0690 (ground-level) and 0.0610 (text) on average for C={6,7,8}Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy