SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification

Abstract

Hyperspectral Image (HSI) classification using Convolutional Neural Networks (CNN) is widely found in the current literature. Approaches vary from using SVMs to 2D CNNs, 3D CNNs, 3D-2D CNNs. Besides 3D-2D CNNs and FuSENet, the other approaches do not consider both the spectral and spatial features together for HSI classification task, thereby resulting in poor performances. 3D CNNs are computationally heavy and are not widely used, while 2D CNNs do not consider multiresolution processing of images, and only limits itself to the spatial features. Even though 3D-2D CNNs try to model the spectral and spatial features their performance seems limited when applied over multiple dataset. In this article, we propose SpectralNET, a wavelet CNN, which is a variation of 2D CNN for multi-resolution HSI classification. A wavelet CNN uses layers of wavelet transform to bring out spectral features. Computing a wavelet transform is lighter than computing 3D CNN. The spectral features extracted are then connected to the 2D CNN which bring out the spatial features, thereby creating a spatialspectral feature vector for classification. Overall a better model is achieved that can classify multi-resolution HSI data with high accuracy. Experiments performed with SpectralNET on benchmark dataset, i.e. Indian Pines, University of Pavia, and Salinas Scenes confirm the superiority of proposed SpectralNET with respect to the state-of-the-art methods. The code is publicly available in https://github.com/tanmay-ty/SpectralNET.

DCCaps-UNet: A U-Shaped Hyperspectral Semantic Segmentation Model Based on the Depthwise Separable and Conditional Convolution Capsule Network

“…In order to further evaluate the performance of the model proposed in this paper, U-Net [40], SS3FCN [36], HybridSN [45], SpectralNet [46], and JigsawHSI [47] algorithms were selected for the comparative analysis. U-Net is the original semantic segmentation algorithm, and this paper also builds the model on this architecture.…”

Hyper-Spectral Imaging for Overlapping Plastic Flakes Segmentation

“…Squeeze-and-Excitation (SE) residual bag-of-feature learning framework used SE blocks and batch normalization to suppress feature maps that are irrelevant to the learning process. SpectralNET [10] used wavelet CNNs instead of a 3D CNN to learn the spectral features as they are computationally lighter compared to a 3D CNN computation. The recent advances in deep learning -attention mechanisms and transformers are also documented in HSI.…”

Hyperspectral Image Classification using Hybrid Deep Convolutional Neural Network

“…In [28] Feng et al The authors presented a multiclass spatial-spectral Generative adversarial networks (GAN) ap-proach that uses generators to create samples and a discrim-inator to extract joint spatialspectral features. The overall accuracy of this approach is 98.2% with 9% percent ratio of testing samples.…”

“…Table 4 shows comparison between the overall accuracy, average accuracy and kappa accuracy for and WavletCNN model having softmax activation function [28]and Hybrid CNN with softmax as an activation function using by author in [29] with our Hybrid CNN model having sigmoid as an activation for classification. And the performance of HbridSN with sigmoid is better than other model proposed by authors in their paper.…”