A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentation

TL;DR

This paper introduces GLCANet, a lightweight global-local cross-attention network that improves semantic segmentation of ultra-high resolution remote sensing images by enhancing feature fusion and computational efficiency.

Contribution

The paper presents a novel dual-stream architecture with self-attention and masked cross-attention mechanisms for efficient global-local feature fusion in UHR remote sensing imagery.

Findings

Outperforms state-of-the-art methods in accuracy

Reduces GPU memory usage significantly

Effectively processes large high-resolution images

Abstract

With the rapid development of ultra-high resolution (UHR) remote sensing technology, the demand for accurate and efficient semantic segmentation has increased significantly. However, existing methods face challenges in computational efficiency and multi-scale feature fusion. To address these issues, we propose GLCANet (Global-Local Cross-Attention Network), a lightweight segmentation framework designed for UHR remote sensing imagery.GLCANet employs a dual-stream architecture to efficiently fuse global semantics and local details while minimizing GPU usage. A self-attention mechanism enhances long-range dependencies, refines global features, and preserves local details for better semantic consistency. A masked cross-attention mechanism also adaptively fuses global-local features, selectively enhancing fine-grained details while exploiting global context to improve segmentation accuracy. Experimental results show that GLCANet outperforms state-of-the-art methods regarding accuracy and computational efficiency. The model effectively processes large, high-resolution images with a small memory footprint, providing a promising solution for real-world remote sensing applications.