ProVG: Progressive Visual Grounding via Language Decoupling for Remote Sensing Imagery

2026-04-02

AI Summary

This work addresses the challenge of grounding natural language expressions in remote sensing images, where fine-grained linguistic cues—such as spatial relations and object attributes—are often underutilized, leading to difficulties in distinguishing visually similar targets. To overcome this limitation, the authors propose a language disentanglement strategy that decomposes referring expressions into global context, spatial relations, and object attributes. They further introduce a progressive cross-modal modulation mechanism—termed “overview–localize–verify”—to enable coarse-to-fine vision–language alignment. Integrated with multi-scale feature fusion and a language-guided calibration decoder, this approach forms a unified multi-task framework capable of both referring expression comprehension and segmentation. Extensive experiments demonstrate that the method achieves state-of-the-art performance on the RRSIS-D and RISBench benchmarks, significantly outperforming existing approaches.

Abstract

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.

Problem

• visual grounding
• remote sensing imagery
• language decoupling
• spatial relations
• object attributes

Innovation

• visual grounding
• language decoupling
• progressive alignment
• remote sensing imagery
• cross-modal modulation