Hierarchical Attention and Parallel Filter Fusion Network for Multi-Source Data Classification

TL;DR

This paper introduces a novel hierarchical attention and parallel filter fusion network that effectively integrates global, spectral, and local features for improved multi-source remote sensing data classification, demonstrating superior accuracy.

Contribution

The paper proposes a new hierarchical attention module and parallel filter fusion module to better exploit multi-source data features for remote sensing classification.

Findings

Achieved 91.44% and 80.51% overall accuracy on two datasets.

Outperformed current state-of-the-art methods.

Validated effectiveness through extensive experiments.

Abstract

Hyperspectral image (HSI) and synthetic aperture radar (SAR) data joint classification is a crucial and yet challenging task in the field of remote sensing image interpretation. However, feature modeling in existing methods is deficient to exploit the abundant global, spectral, and local features simultaneously, leading to sub-optimal classification performance. To solve the problem, we propose a hierarchical attention and parallel filter fusion network for multi-source data classification. Concretely, we design a hierarchical attention module for hyperspectral feature extraction. This module integrates global, spectral, and local features simultaneously to provide more comprehensive feature representation. In addition, we develop parallel filter fusion module which enhances cross-modal feature interactions among different spatial locations in the frequency domain. Extensive experiments on two multi-source remote sensing data classification datasets verify the superiority of our proposed method over current state-of-the-art classification approaches. Specifically, our proposed method achieves 91.44% and 80.51% of overall accuracy (OA) on the respective datasets, highlighting its superior performance.