HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification

Abstract

Hyperspectral image (HSI) classification is widely used for the analysis of remotely sensed images. Hyperspectral imagery includes varying bands of images. Convolutional Neural Network (CNN) is one of the most frequently used deep learning based methods for visual data processing. The use of CNN for HSI classification is also visible in recent works. These approaches are mostly based on 2D CNN. Whereas, the HSI classification performance is highly dependent on both spatial and spectral information. Very few methods have utilized the 3D CNN because of increased computational complexity. This letter proposes a Hybrid Spectral Convolutional Neural Network (HybridSN) for HSI classification. Basically, the HybridSN is a spectral-spatial 3D-CNN followed by spatial 2D-CNN. The 3D-CNN facilitates the joint spatial-spectral feature representation from a stack of spectral bands. The 2D-CNN on top of the 3D-CNN further learns more abstract level spatial representation. Moreover, the use of hybrid CNNs reduces the complexity of the model compared to 3D-CNN alone. To test the performance of this hybrid approach, very rigorous HSI classification experiments are performed over Indian Pines, Pavia University and Salinas Scene remote sensing datasets. The results are compared with the state-of-the-art hand-crafted as well as end-to-end deep learning based methods. A very satisfactory performance is obtained using the proposed HybridSN for HSI classification. The source code can be found at \url{https://github.com/gokriznastic/HybridSN}.

Published in IEEE Geoscience and Remote Sensing Letters

References in corpus (5)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Three dimensional Deep Learning approach for remote sensing image classification
• Advances in Hyperspectral Image Classification: Earth monitoring with statistical learning methods
• RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification
• LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural Networks

Cited by in corpus (39)

• Multimodal Fusion Transformer for Remote Sensing Image Classification
• Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
• A Fast 3D CNN for Hyperspectral Image Classification
• Deep Hyperspectral Unmixing using Transformer Network
• Nearest Neighbor-Based Contrastive Learning for Hyperspectral and LiDAR Data Classification
• Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification
• S${}^2$Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification
• Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification
• AeroRIT: A New Scene for Hyperspectral Image Analysis
• Physically-Constrained Transfer Learning through Shared Abundance Space for Hyperspectral Image Classification
• SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification
• Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
• PolSAR Image Classification using a Hybrid Complex-Valued Network (HybridCVNet)
• Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover Mapping
• Compressive spectral image classification using 3D coded convolutional neural network
• Classification of grapevine varieties using UAV hyperspectral imaging
• Shallow Network Based on Depthwise Over-Parameterized Convolution for Hyperspectral Image Classification
• A CNN with Noise Inclined Module and Denoise Framework for Hyperspectral Image Classification
• A distribution-dependent Mumford-Shah model for unsupervised hyperspectral image segmentation
• DiverGet: A Search-Based Software Testing Approach for Deep Neural Network Quantization Assessment
• Multiscale Principle of Relevant Information for Hyperspectral Image Classification
• HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification
• Terrain Classification using Transfer Learning on Hyperspectral Images: A Comparative study
• Hyperspectral Image Classification: Artifacts of Dimension Reduction on Hybrid CNN
• Hyperspectral Images Classification Based on Multi-scale Residual Network
• LoLA-SpecViT: Local Attention SwiGLU Vision Transformer with LoRA for Hyperspectral Imaging
• EnergyFormer: Energy Attention with Fourier Embedding for Hyperspectral Image Classification
• MixerSENet: A Lightweight Framework for Efficient Hyperspectral Image Classification
• Decision Tree Learning with Spatial Modal Logics
• Hyperspectral Image Classification using Spectral-Spatial Mixer Network
• Importance of Disjoint Sampling in Conventional and Transformer Models for Hyperspectral Image Classification
• Hyperspectral and LiDAR data classification based on linear self-attention
• Improving Deep Hyperspectral Image Classification Performance with Spectral Unmixing
• LiteDepthwiseNet: An Extreme Lightweight Network for Hyperspectral Image Classification
• Learning Hyperspectral Feature Extraction and Classification with ResNeXt Network
• IRX-1D: A Simple Deep Learning Architecture for Remote Sensing Classifications
• A 3D 2D convolutional Neural Network Model for Hyperspectral Image Classification
• Data Efficient Complex Feature Fusion Network For Hyperspectral Image Classification
• MixerCA: An Efficient and Accurate Model for High-Performance Hyperspectral Image Classification