Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation

TL;DR

This paper introduces CroBIM, a novel framework for referring remote sensing image segmentation that effectively integrates spatial and linguistic information through bidirectional cross-modal interactions, achieving superior results on new and existing datasets.

Contribution

The paper proposes CroBIM, a new cross-modal interaction model with modules for context-aware prompt modulation, language-guided feature aggregation, and a mutual-interaction decoder, along with a large-scale benchmark dataset RISBench.

Findings

CroBIM outperforms existing methods on RISBench and other datasets.

The RISBench dataset contains 52,472 image-language-label triplets.

The proposed modules enhance cross-modal feature alignment and segmentation accuracy.

Abstract

Given a natural language expression and a remote sensing image, the goal of referring remote sensing image segmentation (RRSIS) is to generate a pixel-level mask of the target object identified by the referring expression. In contrast to natural scenarios, expressions in RRSIS often involve complex geospatial relationships, with target objects of interest that vary significantly in scale and lack visual saliency, thereby increasing the difficulty of achieving precise segmentation. To address the aforementioned challenges, a novel RRSIS framework is proposed, termed the cross-modal bidirectional interaction model (CroBIM). Specifically, a context-aware prompt modulation (CAPM) module is designed to integrate spatial positional relationships and task-specific knowledge into the linguistic features, thereby enhancing the ability to capture the target object. Additionally, a language-guided feature aggregation (LGFA) module is introduced to integrate linguistic information into multi-scale visual features, incorporating an attention deficit compensation mechanism to enhance feature aggregation. Finally, a mutual-interaction decoder (MID) is designed to enhance cross-modal feature alignment through cascaded bidirectional cross-attention, thereby enabling precise segmentation mask prediction. To further forster the research of RRSIS, we also construct RISBench, a new large-scale benchmark dataset comprising 52,472 image-language-label triplets. Extensive benchmarking on RISBench and two other prevalent datasets demonstrates the superior performance of the proposed CroBIM over existing state-of-the-art (SOTA) methods. The source code for CroBIM and the RISBench dataset will be publicly available at https://github.com/HIT-SIRS/CroBIM