S$^{2}$DCN: Spectral–Spatial Difference Convolution Network for Hyperspectral Image Classification
Open Access
- 3 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 3053-3068
Abstract
A novel spectral–spatial difference convolution network (S $^{2}$ DCN) is proposed for hyperspectral image (HSI) classification, which integrates the difference principle into the deep learning framework. S $^{2}$ DCN employs a learnable gradient encoding pattern to extract important detail features in spectral and spatial domains, alleviating the information loss caused by the oversmoothing effect in deep feature extraction. Specifically, the feature extraction modules in S $^{2}$ DCN are designed, namely spectral difference convolution (SeDC) module and spatial difference convolution (SaDC) module. The SeDC module performs 1-D difference convolution in the spectral domain to capture peak-valley information in sensitive narrow bands, enhance subtle spectral differences, and preserve fine-grained features. The SaDC module employs 2-D difference convolution in the spatial domain, integrating fine-structural features while preserving the deep abstract features extracted by vanilla convolutions. This further empowers the capability of the model to extract discriminative features. A series of experiments are performed on four publicly available HSI datasets to demonstrate the effectiveness of S $^{2}$ DCN method, which is compared with current state-of-the-art models. The experimental results show that the proposed S $^{2}$ DCN outperforms competitors and achieves optimal classification performance.Keywords
This publication has 55 references indexed in Scilit:
- Depth dynamic center difference convolutions for monocular 3D object detectionNeurocomputing, 2022
- Classification of hyperspectral images via improved cycle‐MLPIET Computer Vision, 2022
- A fully convolutional network with channel and spatial attention for hyperspectral image classificationRemote Sensing Letters, 2021
- A survey: Deep learning for hyperspectral image classification with few labeled samplesNeurocomputing, 2021
- M2H-Net: A Reconstruction Method For Hyperspectral Remotely Sensed ImageryISPRS Journal of Photogrammetry and Remote Sensing, 2021
- WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRFRemote Sensing of Environment, 2020
- Spatial‐spectral analysis method using texture features combined with PCA for information extraction in hyperspectral imagesJournal of Chemometrics, 2019
- Spectral-spatial classification of hyperspectral imagery using a dual-channel convolutional neural networkRemote Sensing Letters, 2017
- Deep learning for visual understanding: A reviewNeurocomputing, 2016
- An assessment of independent component analysis for detection of military targets from hyperspectral imagesInternational Journal of Applied Earth Observation and Geoinformation, 2011