A High-Performance Spectral-Spatial Residual Network for Hyperspectral Image Classification with Small Training Data

Khotimah, Wijayanti Nurul; Bennamoun, Mohammed; Boussaid, Farid; Sohel, Ferdous; Edwards, David

doi:10.3390/rs12193137

Cited by 16 publications

(9 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For CS, co(CS), sp(CS), and Kharchia datasets, we compared our model with a model that treated spectral information as a vector and used the standard 1D convolution to extract the features (1D CNN). We also compared the proposed method with the spectral-residual network (sRN), which uses 1D convolution and residual connections [53]. Furthermore, we compared our proposed method with methods that considered the spectral information as a sequence, e.g., RNN, LSTM [54] and spectralFormer [55].…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

SC-CAN: Spectral Convolution and Channel Attention Network for Wheat Stress Classification

et al. 2022

Self Cite

View full text Add to dashboard Cite

Biotic and abiotic plant stress (e.g., frost, fungi, diseases) can significantly impact crop production. It is thus essential to detect such stress at an early stage before visual symptoms and damage become apparent. To this end, this paper proposes a novel deep learning method, called Spectral Convolution and Channel Attention Network (SC-CAN), which exploits the difference in spectral responses of healthy and stressed crops. The proposed SC-CAN method comprises two main modules: (i) a spectral convolution module, which consists of dilated causal convolutional layers stacked in a residual manner to capture the spectral features; (ii) a channel attention module, which consists of a global pooling layer and fully connected layers that compute inter-relationship between feature map channels before scaling them based on their importance level (attention score). Unlike standard convolution, which focuses on learning local features, the dilated convolution layers can learn both local and global features. These layers also have long receptive fields, making them suitable for capturing long dependency patterns in hyperspectral data. However, because not all feature maps produced by the dilated convolutional layers are important, we propose a channel attention module that weights the feature maps according to their importance level. We used SC-CAN to classify salt stress (i.e., abiotic stress) on four datasets (Chinese Spring (CS), Aegilops columnaris (co(CS)), Ae. speltoides auchery (sp(CS)), and Kharchia datasets) and Fusarium head blight disease (i.e., biotic stress) on Fusarium dataset. Reported experimental results show that the proposed method outperforms existing state-of-the-art techniques with an overall accuracy of 83.08%, 88.90%, 82.44%, 82.10%, and 82.78% on CS, co(CS), sp(CS), Kharchia, and Fusarium datasets, respectively.

show abstract

Section: Comparison With Existing Methodsmentioning

confidence: 99%

SC-CAN: Spectral Convolution and Channel Attention Network for Wheat Stress Classification

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among all the different methods, the convolutional neural network (CNN) has shown efficacy in achieving satisfactory performance for HSI classification. With its weight-sharing capability, the CNN reduces the required parameters for image classification [43]. Hu et al [44] introduced one-dimensional CNN (1-D CNN) to extract spectral information of each pixel.…”

Section: Introductionmentioning

confidence: 99%

A Deep Spectral-Spatial Residual Attention Network for Hyperspectral Image Classification

Chhapariya,

Buddhiraju,

Kumar

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In recent years, deep learning algorithms, particularly convolutional neural networks (CNNs), have significantly improved the performance of the hyperspectral image (HSI) classification. However, due to the high dimensionality of HSI and limited training samples, the deep neural network causes model overfitting. Additionally, considering all the bands of HSI datasets equally for feature learning and being unable to distinguish between the edge and the center pixels of a neighborhood reduces classification accuracy. Thus, in this paper, we propose an end-toend deep spectral-spatial residual attention network (DSSpRAN) motivated by the attention mechanism of the human visual system for HSI classification. The DSSpRAN considers input HSI data as a 3-D cube instead of using dimensionality reduction methods. The proposed model simultaneously incorporates spectral and spatial features by considering a spectral residual attention network (SRAN) and a spatial residual attention network (SpRAN). In SRAN, the weights are assigned and learned adaptively to select essential features from each band. The SpRAN enhances the importance of classifying each nearby pixel to the center pixel. It assigns the same label as that of the center pixel to the surrounding pixels, thus limiting pixels with different labels. The proposed method has been evaluated on five different datasets to prove the state-of-the-art for various land use land cover scenarios. A comprehensive qualitative and quantitative analysis of the results shows that the proposed method significantly outperforms other state-of-the-art methods.

show abstract

“…In the field of remote sensing, CNN has also been widely used for the accurate classification of crop, urban land use, wetland, and so on [8][9][10][11]. For the classification of hyperspectral remote sensing, CNN-based methods including 1D, 2D, 3D-CNN, multiscale CNN, residual CNN, and object-based CNN have been proposed [12][13][14][15]. However, CNN failed in learning the spatial hierarchies between features and lost some spatial information (e.g., location) in the pooling layer.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Capsule Network for Hyperspectral Remote Sensing Classification

Ding

Yang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The capsule network (Caps) is a novel type of neural network that has great potential for the classification of hyperspectral remote sensing. However, the Caps suffers from the issue of gradient vanishing. To solve this problem, a powered activation regularization based adaptive capsule network (PAR-ACaps) was proposed for hyperspectral remote sensing classification, in which an adaptive routing algorithm without iteration was applied to amplify the gradient, and the powered activation regularization method was used to learn the sparser and more discriminative representation. The classification performance of PAR-ACaps was evaluated using two public hyperspectral remote sensing datasets, i.e., the Pavia University (PU) and Salinas (SA) datasets. The average overall classification accuracy (OA) of PAR-ACaps with shallower architecture was measured and compared with those of the benchmarks, including random forest (RF), support vector machine (SVM), 1-dimensional convolutional neural network (1DCNN), two-dimensional convolutional neural network (CNN), three-dimensional convolutional neural network (3DCNN), Caps, and the original adaptive capsule network (ACaps) with comparable network architectures. The OA of PAR-ACaps for PU and SA datasets was 99.51% and 94.52%, respectively, which was higher than those of benchmarks. Moreover, the classification performance of PAR-ACaps with relatively deeper neural architecture (four and six convolutional layers in the feature extraction stage) was also evaluated to demonstrate the effectiveness of gradient amplification. As shown in the experimental results, the classification performance of PAR-ACaps with relatively deeper neural architecture for PU and SA datasets was also superior to 1DCNN, CNN, 3DCNN, Caps, and ACaps with comparable neural architectures. Additionally, the training time consumed by PAR-ACaps was significantly lower than that of Caps. The proposed PAR-ACaps is, therefore, recommended as an effective alternative for hyperspectral remote sensing classification.

show abstract

A High-Performance Spectral-Spatial Residual Network for Hyperspectral Image Classification with Small Training Data

Cited by 16 publications

References 62 publications

SC-CAN: Spectral Convolution and Channel Attention Network for Wheat Stress Classification

SC-CAN: Spectral Convolution and Channel Attention Network for Wheat Stress Classification

A Deep Spectral-Spatial Residual Attention Network for Hyperspectral Image Classification

An Adaptive Capsule Network for Hyperspectral Remote Sensing Classification

Contact Info

Product

Resources

About