MSHCNet: Multi-Stream Hybridized Convolutional Networks with Mixed Statistics in Euclidean/Non-Euclidean Spaces and Its Application to Hyperspectral Image Classification

TL;DR

This paper introduces MSHCNet, a multi-stream hybrid convolutional network that combines Euclidean and non-Euclidean features for hyperspectral image classification, significantly improving accuracy over existing methods.

Contribution

The paper proposes a novel multi-stream network with graph-based second-order pooling and multi-view feature fusion for enhanced hyperspectral image classification.

Findings

MSHCNet outperforms eight state-of-the-art methods on three datasets.

The multi-stream approach effectively captures complementary spatial-spectral information.

Graph-based second-order pooling improves boundary delineation in hyperspectral images.

Abstract

It is well known that hyperspectral images (HSI) contain rich spatial-spectral contextual information, and how to effectively combine both spectral and spatial information using DNN for HSI classification has become a new research hotspot. Compared with CNN with square kernels, GCN have exhibited exciting potential to model spatial contextual structure and conduct flexible convolution on arbitrarily irregular image regions. However, current GCN only using first-order spectral-spatial signatures can result in boundary blurring and isolated misclassification. To address these, we first designed the graph-based second-order pooling (GSOP) operation to obtain contextual nodes information in non-Euclidean space for GCN. Further, we proposed a novel multi-stream hybridized convolutional network (MSHCNet) with combination of first and second order statistics in Euclidean/non-Euclidean spaces to learn and fuse multi-view complementary information to segment HSIs. Specifically, our MSHCNet adopted four parallel streams, which contained G-stream, utilizing the irregular correlation between adjacent land covers in terms of first-order graph in non-Euclidean space; C-stream, adopting convolution operator to learn regular spatial-spectral features in Euclidean space; N-stream, combining first and second order features to learn representative and discriminative regular spatial-spectral features of Euclidean space; S-stream, using GSOP to capture boundary correlations and obtain graph representations from all nodes in graphs of non-Euclidean space. Besides, these feature representations learned from four different streams were fused to integrate the multi-view complementary information for HSI classification. Finally, we evaluated our proposed MSHCNet on three hyperspectral datasets, and experimental results demonstrated that our method significantly outperformed state-of-the-art eight methods.