Hyperspectral Image Classification via Spatial Shuffle-Based Convolutional Neural Network

Abstract

The unique spatial–spectral integration characteristics of hyperspectral imagery (HSI) make it widely applicable in many fields. The spatial–spectral feature fusion-based HSI classification has always been a research hotspot. Typically, classification methods based on spatial–spectral features will select larger neighborhood windows to extract more spatial features for classification. However, this approach can also lead to the problem of non-independent training and testing sets to a certain extent. This paper proposes a spatial shuffle strategy that selects a smaller neighborhood window and randomly shuffles the pixels within the window. This strategy simulates the potential patterns of the pixel distribution in the real world as much as possible. Then, the samples of a three-dimensional HSI cube is transformed into two-dimensional images. Training with a simple CNN model that is not optimized for architecture can still achieve very high classification accuracy, indicating that the proposed method of this paper has considerable performance-improvement potential. The experimental results also indicate that the smaller neighborhood windows can achieve the same, or even better, classification performance compared to larger neighborhood windows.

Vision Transformer-Based Ensemble Learning for Hyperspectral Image Classification

“…In order to address the aforementioned issues, Wang et.al [53] proposes a strategy called "spatial shuffle". After obtaining the neighboring pixels of each training sample, this strategy involves randomly shuffling the positions of the pixels within the neighborhood, excluding the center pixel.…”

“…Based on the principle of spatial shuffle and considering the requirements of the ViT for input data, the following preprocessing steps, which are the same as Ref. [53], are performed for HSI training samples:…”