Search papers, labs, and topics across Lattice.
This paper introduces ProVG, a novel remote sensing visual grounding (RSVG) framework that enhances localization accuracy by decoupling language expressions into global context, spatial relations, and object attributes. ProVG employs a progressive cross-modal modulator within a survey-locate-verify scheme to dynamically modulate visual attention for coarse-to-fine vision-language alignment. Experiments on RRSIS-D and RISBench show ProVG achieves state-of-the-art performance, outperforming existing methods.
By explicitly disentangling language into global context, spatial relations, and object attributes, ProVG achieves state-of-the-art remote sensing visual grounding, suggesting that fine-grained linguistic cues are key to unlocking performance in this domain.
Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing imagery according to natural language expressions. Previous methods typically rely on sentence-level vision-language alignment, which struggles to exploit fine-grained linguistic cues, such as \textit{spatial relations} and \textit{object attributes}, that are crucial for distinguishing objects with similar characteristics. Importantly, these cues play distinct roles across different grounding stages and should be leveraged accordingly to provide more explicit guidance. In this work, we propose \textbf{ProVG}, a novel RSVG framework that improves localization accuracy by decoupling language expressions into global context, spatial relations, and object attributes. To integrate these linguistic cues, ProVG employs a simple yet effective progressive cross-modal modulator, which dynamically modulates visual attention through a \textit{survey-locate-verify} scheme, enabling coarse-to-fine vision-language alignment. In addition, ProVG incorporates a cross-scale fusion module to mitigate the large-scale variations in remote sensing imagery, along with a language-guided calibration decoder to refine cross-modal alignment during prediction. A unified multi-task head further enables ProVG to support both referring expression comprehension and segmentation tasks. Extensive experiments on two benchmarks, \textit{i.e.}, RRSIS-D and RISBench, demonstrate that ProVG consistently outperforms existing methods, achieving new state-of-the-art performance.
