Semisupervised Classification of Hyperspectral Image Based on Graph Convolutional Broad Network

Wang, Haoyu; Cheng, Yuhu; Chen, C. L. Philip; Wang, Xuesong

doi:10.1109/jstars.2021.3062642

Cited by 17 publications

(9 citation statements)

References 43 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to evaluate the classification performance of this method, we compare our method with traditional machine learning methods and deep learning methods.Traditional machine learning methods include SVMCK [28] and ELMCK [29]; broad learning system methods include BLS [18], SBLS [20], LBP-BLS [21]; deep learning methods include GCN [10], SSGCN [14], MDGCN [16], 2DCNN [30], GCBN [31]. The comparison method is described below.…”

Section: Compared Methods and Experimental Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Graph Convolutional Enhanced Discriminative Broad Learning System for Hyperspectral Image Classification

Tuya

2022

IEEE Access

View full text Add to dashboard Cite

Recently, broad learning system (BLS) have demonstrated excellent performance in hyperspectral images (HSI) classification. However, due to the complex geometric structure and spatial layout of HSI, the linear sparse features in broad learning system are difficult to fully represent hyperspectral data. In addition, the features learned by broad learning system lack more effective discriminative ability, which leads to the limited expressive ability of features. To address the issues, we propose a graph convolutional enhanced discriminative broad learning system (GCDBLS) for HSI Classification. GCDBLS aggregates the node information in the adjacency graph through graph convolution, and then learns the context relationship, so as to obtain rich nonlinear spatial spectral features in hyperspectral images; In order to extract more discriminative hyperspectral image features, GCDBLS introduces the concept of local intra-class scatter and local inter-class scatter. By minimizing the local intraclass feature distance and maximizing the local inter-class feature distance, GCDBLS can improve the discrimination ability of BLS extracted features. On three HSI datasets, the experiments compared with the latest classification methods show that the proposed method achieves good results, and improves the classification performance of hyperspectral images.INDEX TERMS broad learning system; hyperspectral image; graph convolutional; Intra-class feature distance；Inter-class feature distance.

show abstract

Section: Compared Methods and Experimental Settingsmentioning

confidence: 99%

“…(9) MDGCN: Wan et al[16] used superpixel segmentation on HSI and adopted multi-scale GCN to extract HSI multiscale graph features. (10) GCBN: Wang et al[31] proposed a graph convolutional broad network (GCBN) and apply it for hyperspectral image classification.…”

mentioning

confidence: 99%

Graph Convolutional Enhanced Discriminative Broad Learning System for Hyperspectral Image Classification

Tuya

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…As mentioned in the section III-C, F = WF u . The label propagation for the AG-based SSL model can be represented as: (15) where F l = W l F u , and T l is the labels of labeled pixels. η is the parameter of regularization term.…”

Section: E Ag-based Ssl Modelmentioning

confidence: 99%

“…Feng et al [14] combined collaborative learning and attention mechanism to generate high-quality samples for HSI, where the features of real multiclass samples assist the sample generation in the generator, improving the classification performance of the discriminator. These methods are usually based on pattern recognition algorithms, e.g., random forest (RF), support vector machine (SVM) and k-nearest neighbor (kNN) [15]. The more training data is used to achieve the better classification performance of supervised approaches.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Imagery Classification via Random Multigraphs Ensemble Learning

Miao

Chen

Yuan

et al. 2022

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

View full text Add to dashboard Cite

Hyperspectral imagery (HSI) classification, which attempts to assign hyperspectral pixels with proper labels, has drawn significant attention in various applications. Recently, the graph-based semi-supervised learning (SSL) approaches have shown the outstanding ability to handle the situation of limited labeled data for classification task. However, it is hard to construct the pairwise adjacent graph due to the high dimensionality of hyperspectral data. Besides, the graph-based SSL models are usually decided by a single classifier, which fail to effectively learn the complex structures and intrinsic properties of HSI. To address these problems, we propose a novel graph-based SSL classification model for HSI, which is based on Random Multi-Graphs construction and Ensemble strategy (RMGE). Specifically, the anchor graph (AG) is constructed with spatial-spectral features, which integrates the spatial characteristics extracted by local binary pattern (LBP) on each selected spectrum, preserving fine structures of local region. In order to enhance the discriminative capability of the classifier and avoid the trivial solution, the maximum entropy regularization is added into adjacent AG model. In addition, to capture the diversity of HSI data effectively, we design the ensemble framework by employing multiple AGs to learn HSI features. Experiments conducted on real hyperspectral datasets indicate that the proposed RMGE shows better performance than that of state-of-the-art approaches.

show abstract

“…[11] proposes a semi-supervised graph based HSI classification. [12] proposes semi-supervised graph neural network, [13], [14] utilizes graph convolution networks for semi-supervised HSI classification. In case of unsupervised approaches, the most widely used approach is that of spectral clustering [15].…”

Section: Introductionmentioning

confidence: 99%

ESW Edge-Weights : Ensemble Stochastic Watershed Edge-Weights for Hyperspectral Image Classification

Agarwal,

Aziz,

Krishnan

et al. 2022

Preprint

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification is a topic of active research. One of the main challenges of HSI classification is the lack of reliable labelled samples. Various semisupervised and unsupervised classification methods are proposed to handle the low number of labelled samples. Chief among them are graph convolution networks (GCN) and their variants. These approaches exploit the graph structure for semi-supervised and unsupervised classification. While several of these methods implicitly construct edge-weights, to our knowledge, not much work has been done to estimate the edge-weights explicitly. In this article, we estimate the edge-weights explicitly and use them for the downstream classification tasks -both semi-supervised and unsupervised. The proposed edge-weights are based on two key insights -(a) Ensembles reduce the variance and (b) Classes in HSI datasets and feature similarity have only onesided implications. That is, while same classes would have similar features, similar features do not necessarily imply same classes. Exploiting these, we estimate the edge-weights using an aggregate of ensembles of watersheds over subsamples of features. These edge weights are evaluated for both semi-supervised and unsupervised classification tasks. The evaluation for semi-supervised tasks uses Random-Walk based approach. For the unsupervised case, we use a simple filter using a graph convolution network (GCN). In both these cases, the proposed edge weights outperform the traditional approaches to compute edge-weights -Euclidean distances and cosine similarities. Fascinatingly, with the proposed edge-weights, the simplest GCN obtained results comparable to the recent state-of-the-art.

show abstract

Semisupervised Classification of Hyperspectral Image Based on Graph Convolutional Broad Network

Cited by 17 publications

References 43 publications

Graph Convolutional Enhanced Discriminative Broad Learning System for Hyperspectral Image Classification

Graph Convolutional Enhanced Discriminative Broad Learning System for Hyperspectral Image Classification

Hyperspectral Imagery Classification via Random Multigraphs Ensemble Learning

ESW Edge-Weights : Ensemble Stochastic Watershed Edge-Weights for Hyperspectral Image Classification

Contact Info

Product

Resources

About