Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention

TL;DR

This paper introduces VPR-AttLLM, a framework that enhances visual place recognition for crowdsourced flood images by integrating LLM-guided attention, significantly improving geo-localization accuracy without retraining models.

Contribution

It presents a novel, model-agnostic approach that leverages LLMs for attention-guided descriptor enhancement, improving robustness and accuracy in flood image geo-localization.

Findings

Improves recall by 1-3% on standard benchmarks.

Achieves up to 8% improvement on real flood imagery.

Enhances cross-source robustness without retraining models.

Abstract

Crowdsourced social media imagery provides real-time visual evidence of urban flooding but often lacks reliable geographic metadata for emergency response. Existing Visual Place Recognition (VPR) models struggle to geo-localize these images due to cross-source domain shifts and visual distortions. We present VPR-AttLLM, a model-agnostic framework integrating the semantic reasoning and geospatial knowledge of Large Language Models (LLMs) into VPR pipelines via attention-guided descriptor enhancement. VPR-AttLLM uses LLMs to isolate location-informative regions and suppress transient noise, improving retrieval without model retraining or new data. We evaluate this framework across San Francisco and Hong Kong using established queries, synthetic flooding scenarios, and real social media flood images. Integrating VPR-AttLLM with state-of-the-art models (CosPlace, EigenPlaces, SALAD) consistently improves recall, yielding 1-3% relative gains and up to 8% on challenging real flood imagery. By embedding urban perception principles into attention mechanisms, VPR-AttLLM bridges human-like spatial reasoning with modern VPR architectures. Its plug-and-play design and cross-source robustness offer a scalable solution for rapid geo-localization of crowdsourced crisis imagery, advancing cognitive urban resilience.