A Triple-Path Spectral–Spatial Network With Interleave-Attention for Hyperspectral Image Classification

Abstract

To exploit hyperspectral image's (HSI) spectral–spatial information and reduce network complexity, a triple-path convolution neural network with an interleave-attention mechanism is constructed for high-precision classification. A hybrid branch is proposed to capture joint features, which are later utilized as complementary information for purely spectral and spatial features. Furthermore, the interleave-attention mechanism is elaborately designed to increase the interaction of data from spectral, spatial, and joint branches as they propagate through the network for feature integration. Meanwhile, two attention modules are adopted in the corresponding branch to optimize extracted features for better feature representation. We utilize several real HSI datasets to evaluate network performance, which demonstrates that the proposed triple-path network can obtain very satisfactory performance with fewer parameters and low computational complexity.

Keywords

• Hyperspectral image (HSI) classification
• interleave-attention
• spectral and spatial attention block
• spectral–spatial feature extraction
• triple-path network (TP-Net)