A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification

TL;DR

This paper introduces a novel spectral-spatial-dependent global learning framework that effectively handles insufficient and imbalanced hyperspectral image classification by integrating global convolutional LSTM and attention mechanisms.

Contribution

The proposed SSDGL framework combines GCL and GJAM modules with a balanced sampling strategy to improve feature extraction and classification in imbalanced hyperspectral datasets.

Findings

SSDGL outperforms state-of-the-art methods on three public datasets.

The GCL module effectively captures spectral dependencies.

The GJAM module enhances discriminative feature learning.

Abstract

Deep learning techniques have been widely applied to hyperspectral image (HSI) classification and have achieved great success. However, the deep neural network model has a large parameter space and requires a large number of labeled data. Deep learning methods for HSI classification usually follow a patchwise learning framework. Recently, a fast patch-free global learning (FPGA) architecture was proposed for HSI classification according to global spatial context information. However, FPGA has difficulty extracting the most discriminative features when the sample data is imbalanced. In this paper, a spectral-spatial dependent global learning (SSDGL) framework based on global convolutional long short-term memory (GCL) and global joint attention mechanism (GJAM) is proposed for insufficient and imbalanced HSI classification. In SSDGL, the hierarchically balanced (H-B) sampling strategy and the weighted softmax loss are proposed to address the imbalanced sample problem. To effectively distinguish similar spectral characteristics of land cover types, the GCL module is introduced to extract the long short-term dependency of spectral features. To learn the most discriminative feature representations, the GJAM module is proposed to extract attention areas. The experimental results obtained with three public HSI datasets show that the SSDGL has powerful performance in insufficient and imbalanced sample problems and is superior to other state-of-the-art methods. Code can be obtained at: https://github.com/dengweihuan/SSDGL.