A Fast Dense Spectral–Spatial Convolution Network Framework for Hyperspectral Images Classification

Wang, Wenju; Dou, Shuguang; Jiang, Zhongmin; Sun, Liujie

doi:10.3390/rs10071068

Cited by 269 publications

(151 citation statements)

References 18 publications

Supporting

Mentioning

150

Contrasting

Order By: Relevance

“…In this section, we compare the proposed AUSSC framework with deep learning-based methods, including SAE-LR [14], CNN [18], SSRN [21], 3D-GAN [24], and FDSSC [22]. As SSRN, FDSSC, and the proposed AUSSC are all 3D CNN-based methods, the input spatial size was fixed at 9 × 9 to allow a fair comparison.…”

Section: Resultsmentioning

confidence: 99%

“…Three-dimensional (3D) CNNs have also been used as feature extraction models to acquire spectral-spatial features from HSIs [15]. Two-layer 3D CNNs have performed far better than 2D CNN-based methods [16].Recently, two deep convolutional spectral-spatial networks, the spectral-spatial residual network (SSRN) [17] and the fast and dense spectral-spatial convolutional network (FDSSC) [18], achieved unprecedented classification accuracy. This was due in part to the inclusion of deeper 3D CNN architectures.…”

mentioning

confidence: 99%

“…Recently, two deep convolutional spectral-spatial networks, the spectral-spatial residual network (SSRN) [17] and the fast and dense spectral-spatial convolutional network (FDSSC) [18], achieved unprecedented classification accuracy. This was due in part to the inclusion of deeper 3D CNN architectures.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Alternately Updated Spectral–Spatial Convolution Network for the Classification of Hyperspectral Images

Wang

Dou

Wang³

2019

Remote Sensing

Self Cite

View full text Add to dashboard Cite

The connection structure in the convolutional layers of most deep learning-based algorithms used for the classification of hyperspectral images (HSIs) has typically been in the forward direction. In this study, an end-to-end alternately updated spectral–spatial convolutional network (AUSSC) with a recurrent feedback structure is used to learn refined spectral and spatial features for HSI classification. The proposed AUSSC includes alternating updated blocks in which each layer serves as both an input and an output for the other layers. The AUSSC can refine spectral and spatial features many times under fixed parameters. A center loss function is introduced as an auxiliary objective function to improve the discrimination of features acquired by the model. Additionally, the AUSSC utilizes smaller convolutional kernels than other convolutional neural network (CNN)-based methods to reduce the number of parameters and alleviate overfitting. The proposed method was implemented on four HSI data sets, as follows: Indian Pines, Kennedy Space Center, Salinas Scene, and Houston. Experimental results demonstrated that the proposed AUSSC outperformed the HSI classification accuracy obtained by state-of-the-art deep learning-based methods with a small number of training samples.

show abstract

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Alternately Updated Spectral–Spatial Convolution Network for the Classification of Hyperspectral Images

Wang

Dou

Wang³

2019

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we compare NG-APC model with the classical SVM, the new 1D-CNN [28,29] 2D-CNN [30], 3D-CNN algorithms [31][32][33][34], and RNN [35]. We refer some of these algorithms by nshaud/DeepHyperX on GitHub.…”

Section: Resultsmentioning

confidence: 99%

A hyperspectral image classification algorithm based on atrous convolution

Zhang

Zheng

Liu

et al. 2019

J Wireless Com Network

View full text Add to dashboard Cite

Hyperspectral images not only have high spectral dimension, but the spatial size of datasets containing such kind of images is also small. Aiming at this problem, we design the NG-APC (non-gridding multi-level concatenated Atrous Pyramid Convolution) module based on the combined atrous convolution. By expanding the receptive field of three layers convolution from 7 to 45, the module can obtain a distanced combination of the spectral features of hyperspectral pixels and solve the gridding problem of atrous convolution. In NG-APC module, we construct a 15layer Deep Convolutional Neural Networks (DCNN) model to classify each hyperspectral pixel. Through the experiments on the Pavia University dataset, the model reaches 97.9% accuracy while the parameter amount is only 0.25 M. Compared with other CNN algorithms, our method gets the best OA (Over All Accuracy) and Kappa metrics, at the same time, NG-APC module keeps good performance and high efficiency with smaller number of parameters.

show abstract

“…Furthermore, dense convolutional networks (DenseNet) have demonstrated significant achievement in deep learning network models and have also been used for HSI classification [28][29][30], particularly in limited training samples, because the dense connections have a regularizing effect, which reduces overfitting on tasks with smaller training set sizes [31]. In Reference [21], a 3D dense convolutional network with multiple scales dilated convolutions [32] and a spectral-wise attention mechanism (MSDN-SA) is proposed for HSI classification with limited training samples.…”

Section: Introductionmentioning

confidence: 99%

Combining Spectral Unmixing and 3D/2D Dense Networks with Early-Exiting Strategy for Hyperspectral Image Classification

Fang

Bai

2020

Remote Sensing

View full text Add to dashboard Cite

Recently, Hyperspectral Image (HSI) classification methods based on deep learning models have shown encouraging performance. However, the limited numbers of training samples, as well as the mixed pixels due to low spatial resolution, have become major obstacles for HSI classification.To tackle these problems, we propose a resource-efficient HSI classification framework which introduces adaptive spectral unmixing into a 3D/2D dense network with early-exiting strategy. More specifically, on one hand, our framework uses a cascade of intermediate classifiers throughout the 3D/2D dense network that is trained end-to-end. The proposed 3D/2D dense network that integrates 3D convolutions with 2D convolutions is more capable of handling spectral-spatial features, while containing fewer parameters compared with the conventional 3D convolutions, and further boosts the network performance with limited training samples. On another hand, considering the existence of mixed pixels in HSI data, the pixels in HSI classification are divided into hard samples and easy samples. With the early-exiting strategy in these intermediate classifiers, the average accuracy can be improved by reducing the amount of computation cost for easy samples, thus focusing on classifying hard samples. Furthermore, for hard samples, an adaptive spectral unmixing method is proposed as a complementary source of information for classification, which brings considerable benefits to the final performance. Experimental results on four HSI benchmark datasets demonstrate that the proposed method can achieve better performance than state-of-the-art deep learning-based methods and other traditional HSI classification methods.

show abstract

A Fast Dense Spectral–Spatial Convolution Network Framework for Hyperspectral Images Classification

Cited by 269 publications

References 18 publications

Alternately Updated Spectral–Spatial Convolution Network for the Classification of Hyperspectral Images

Alternately Updated Spectral–Spatial Convolution Network for the Classification of Hyperspectral Images

A hyperspectral image classification algorithm based on atrous convolution

Combining Spectral Unmixing and 3D/2D Dense Networks with Early-Exiting Strategy for Hyperspectral Image Classification

Contact Info

Product

Resources

About