A Survey of Graph and Attention Based Hyperspectral Image Classification Methods for Remote Sensing Data

TL;DR

This survey reviews recent graph and attention-based deep learning methods for hyperspectral image classification in remote sensing, highlighting techniques that incorporate all spectral bands and utilize graph and attention mechanisms for improved feature extraction.

Contribution

It provides a comprehensive summary of graph and attention-based hyperspectral image classification methods, datasets, and benchmarking approaches, highlighting recent advances and trends.

Findings

Graph and attention mechanisms enhance spectral-spatial feature extraction.

All-band methods with attention improve classification accuracy.

Benchmark datasets facilitate fair comparison of techniques.

Abstract

The use of Deep Learning techniques for classification in Hyperspectral Imaging (HSI) is rapidly growing and achieving improved performances. Due to the nature of the data captured by sensors that produce HSI images, a common issue is the dimensionality of the bands that may or may not contribute to the label class distinction. Due to the widespread nature of class labels, Principal Component Analysis is a common method used for reducing the dimensionality. However,there may exist methods that incorporate all bands of the Hyperspectral image with the help of the Attention mechanism. Furthermore, to yield better spectral spatial feature extraction, recent methods have also explored the usage of Graph Convolution Networks and their unique ability to use node features in prediction, which is akin to the pixel spectral makeup. In this survey we present a comprehensive summary of Graph based and Attention based methods to perform Hyperspectral Image Classification for remote sensing and aerial HSI images. We also summarize relevant datasets on which these techniques have been evaluated and benchmark the processing techniques.