Multilevel Superpixel Structured Graph U-Nets for Hyperspectral Image Classification

Liu, Qichao; Xiao, Liang; Yang, Jingxiang; Wei, Zhihui

doi:10.1109/tgrs.2021.3112586

Cited by 37 publications

(24 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the effectiveness of our proposed ConGCN method, other state-of-the-art HSI classification methods are also utilized for comparison. Concretely, we adopt three GCN-based methods, namely, dual-level deep Spatial Manifold Representation (SMR) network [40], Multilevel Superpixel Structured Graph U-net (MSSGU) [41], and Superpixel Graph Learning (SGL) [42]. Besides, one contrastive learning based method [12] termed "Self-Supervised Contrastive Learning" (SSCL) is employed for comparison.…”

Section: Methodsmentioning

confidence: 99%

Hyperspectral Image Classification With Contrastive Graph Convolutional Network

Yu¹,

Wan²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Hyperspectral Image Classification With Contrastive Graph Convolutional Network

Yu¹,

Wan²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…A stacked autoencoder network (SAE) consisting of stacks of shallow autoencoders have also become more popular. Recently, Liu et al [32] integrated GCN and superpixel segmentation technique [24] into a SAE network, which also provided a new idea for applying the SAE network. This research takes SAE as the main framework.…”

Section: A Stacked Autoencoder Network Based On Graph Convolutionmentioning

confidence: 99%

“…The SAE network based on graph convolution proposed by Liu et al [32] performs well in the feature extraction stage but ignores the spectral similarity between pixels in the classification stage. Xue et al [26] proposed that the SGR method fully considers the spectral similarity between pixels in the classification stage.…”

Section: A Gae-sgrnetmentioning

confidence: 99%

See 1 more Smart Citation

Graph-Based Semisupervised Learning With Weighted Features for Hyperspectral Remote Sensing Image Classification

Wang

Zhang

et al. 2022

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

View full text Add to dashboard Cite

Graph neural network has excellent performance in obtaining the similarity relationship of samples, so it has been widely used in computer vision. But hyperspectral remote sensing image (HSI) has some problems such as data redundancy, noise, lack of labeled samples, and insufficient utilization of spatial information. These problems affect the accuracy of HSI classification using graph neural networks. To solve the above problems, this paper proposes graph-based semi-supervised learning with weighted features for HSI classification. The method proposed in this paper first uses the stacked autoencoder network to extract features, which is used to remove the redundancy of HSI data. Then, the similarity attenuation coefficient is introduced to improve the original feature weighting scheme. In this way, the contribution difference of adjacent pixels to the center pixel is reflected. Finally, to obtain more generalized spectral features, a shallow feature extraction mechanism is added to the stacked autoencoder network. And features that have good generalization can solve the problem of the lack of labeled samples. The experiment on three different types of datasets demonstrates that the proposed method in this paper can get better classification performance in the case of the scarcity of labeled samples than other classification methods.

show abstract

“…However, these methods simply extract shallow features based on the spectral information of the HSI, using one single pixel and all of its bands as input. Thus, these linear and nonlinear classifiers do not adapt well to the high dimensionality of the spectrum, limiting their application [18]. Feature extraction (FE) methods are well adapted to the high-dimensionality of the spectrum by mapping the raw HSIs to a low-dimensional space.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Spectral–Spatial Residual Attention Network for Hyperspectral Image Classification

Zhan

Dong

2022

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

View full text Add to dashboard Cite

Deep learning has achieved good performance in hyperspectral image classification (HSIC). Many methods based on deep learning use deep and complex network structures to extract rich spectral and spatial features of hyperspectral images (HSIs) with high accuracy. During the process, how to accurately extract the features and information from pixel blocks in HSIs is important. All of the spectral features are treated equally in classification, and the input of the network often contains much useless pixel information, leading to a low classification result. To solve this problem, an enhanced spectral-spatial residual attention network (ESSRAN) is proposed for HSIC in this paper. In the proposed network, the spectral-spatial attention network (SSAN), residual network (ResNet) and long-short term memory (LSTM) are combined to extract more discriminative spectral and spatial features. More specifically, SSAN is first applied to extract image features by using the spectral attention module to emphasize useful bands and suppress useless bands. The spatial attention module is used to emphasize pixels that have same category with the central pixel. Then, these obtained features are fed into an improved ResNet, which adopts LSTM to learn representative high-level semantic features of the spectral sequences, since the use of ResNet can prevent gradient disappearance and explosion. The proposed ESSRAN model is implemented on three commonly used HSI datasets and compared to some state-of-the-art methods. The results confirm that ESSRAN effectively improves accuracy.

show abstract

Multilevel Superpixel Structured Graph U-Nets for Hyperspectral Image Classification

Cited by 37 publications

References 40 publications

Hyperspectral Image Classification With Contrastive Graph Convolutional Network

Hyperspectral Image Classification With Contrastive Graph Convolutional Network

Graph-Based Semisupervised Learning With Weighted Features for Hyperspectral Remote Sensing Image Classification

Enhanced Spectral–Spatial Residual Attention Network for Hyperspectral Image Classification

Contact Info

Product

Resources

About