CroBIM-U: Uncertainty-Driven Referring Remote Sensing Image Segmentation
This work addresses the challenge of reliably localizing targets described by language in remote sensing imagery, which is crucial for applications like environmental monitoring and urban planning, but it is incremental as it builds on existing methods by adding uncertainty-driven modules.
The paper tackles the problem of referring remote sensing image segmentation, where cross-modal alignment reliability varies spatially due to scale variations and distractors, by proposing an uncertainty-guided framework that uses a pixel-wise uncertainty map to adaptively modulate language fusion and refinement. The result is a plug-and-play solution that significantly improves robustness and geometric fidelity in complex scenes without altering the backbone architecture, as demonstrated through extensive experiments.
Referring remote sensing image segmentation aims to localize specific targets described by natural language within complex overhead imagery. However, due to extreme scale variations, dense similar distractors, and intricate boundary structures, the reliability of cross-modal alignment exhibits significant \textbf{spatial non-uniformity}. Existing methods typically employ uniform fusion and refinement strategies across the entire image, which often introduces unnecessary linguistic perturbations in visually clear regions while failing to provide sufficient disambiguation in confused areas. To address this, we propose an \textbf{uncertainty-guided framework} that explicitly leverages a pixel-wise \textbf{referring uncertainty map} as a spatial prior to orchestrate adaptive inference. Specifically, we introduce a plug-and-play \textbf{Referring Uncertainty Scorer (RUS)}, which is trained via an online error-consistency supervision strategy to interpretably predict the spatial distribution of referential ambiguity. Building on this prior, we design two plug-and-play modules: 1) \textbf{Uncertainty-Gated Fusion (UGF)}, which dynamically modulates language injection strength to enhance constraints in high-uncertainty regions while suppressing noise in low-uncertainty ones; and 2) \textbf{Uncertainty-Driven Local Refinement (UDLR)}, which utilizes uncertainty-derived soft masks to focus refinement on error-prone boundaries and fine details. Extensive experiments demonstrate that our method functions as a unified, plug-and-play solution that significantly improves robustness and geometric fidelity in complex remote sensing scenes without altering the backbone architecture.