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

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.

14 pages,14 figures

References in corpus (8)

• Going Deeper with Contextual CNN for Hyperspectral Image Classification
• Three dimensional Deep Learning approach for remote sensing image classification
• Cascaded Recurrent Neural Networks for Hyperspectral Image Classification
• Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network
• Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
• Spatial-Spectral Feature Extraction via Deep ConvLSTM Neural Networks for Hyperspectral Image Classification
• FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification
• Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification

Cited by in corpus (8)

• MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification
• Robust deep learning-based semantic organ segmentation in hyperspectral images
• Universal Domain Adaptation for Remote Sensing Image Scene Classification
• Content-driven Magnitude-Derivative Spectrum Complementary Learning for Hyperspectral Image Classification
• Unmixing based PAN guided fusion network for hyperspectral imagery
• Enhancing Hyperspectral Image Prediction with Contrastive Learning in Low-Label Regime
• Rega-Net:Retina Gabor Attention for Deep Convolutional Neural Networks
• OOD-SEG: Exploiting out-of-distribution detection techniques for learning image segmentation from sparse multi-class positive-only annotations