Semisupervised graph convolutional network for hyperspectral image classification

Liu, Bing; Gao, Kuiliang; Yu, Anzhu; Guo, Wenyue; Wang, Ruirui; Zuo, Xibing

doi:10.1117/1.jrs.14.026516

Cited by 24 publications

(22 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shahraki and Prasad (2018) defined three spectral-spatial weighted affinities, (1) unsupervised adjacency matrix by using the raw reflectance spectra, (2) supervised adjacency matrix through extracting discriminative features using CNN, and (3) semi-supervised adjacency matrix via learning the limited amount of labeled samples and extensive unlabeled samples, to demonstrate the data resided on manifold structure (i.e., graph structure) [52]. Liu et al (2020) extracted the extended morphological profiles and then conducted graph construction by the k-neighbors method, then fed into a GCN framework [20].…”

Section: Related Workmentioning

confidence: 99%

“…The distance metric of all sample pairs can form a symmetric distance matrix A m = a ij ∈ R n×n . For example, a ij at row i and column j in the matrix A m denotes the distance between the i th pixel and the j th pixel [20].…”

Section: Adjacency Matrixmentioning

confidence: 99%

“…presented a multiscale super pixel segmentation method to model the distribution of classes based on spatial information [19]. Henceforward, the deep learning technique has been increasingly favored by the scientific community attributing to its great power of abstracting representations to classify hyperspectral cubes into certain land cover categories [20][21][22][23]. As a consequence, Cui et al (2019) proposed a multiscale spatial-spectral convolutional neural network (CNN) to integrate multiple receptive fields fused features and multiscale spatial features at different levels [24].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hyperspectral Image Classification with Localized Graph Convolutional Filtering

Sun

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The nascent graph representation learning has shown superiority for resolving graph data. Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships. Faced with hyperspectral image (HSI) classification, the priority problem might be how to convert hyperspectral data into irregular domains from regular grids. In this regard, we present a novel method that performs the localized graph convolutional filtering on HSIs based on spectral graph theory. First, we conducted principal component analysis (PCA) preprocessing to create localized hyperspectral data cubes with unsupervised feature reduction. These feature cubes combined with localized adjacent matrices were fed into the popular graph convolution network in a standard supervised learning paradigm. Finally, we succeeded in analyzing diversified land covers by considering local graph structure with graph convolutional filtering. Experiments on real hyperspectral datasets demonstrated that the presented method offers promising classification performance compared with other popular competitors.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Adjacency Matrixmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Image Classification with Localized Graph Convolutional Filtering

Sun

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…erefore, remote sensing image classification based on CNN has attracted special research interest [24]. Liu et al used the Siamese convolution network to classify remote sensing images and achieved better classification results [25]. Chen et al proposed a 3D-CNN model which utilized local hyperspectral data cubes as input to excavate spatial and spectral information.…”

Section: Introductionmentioning

confidence: 99%

“…Chen et al proposed a 3D-CNN model which utilized local hyperspectral data cubes as input to excavate spatial and spectral information. Zhao and Du developed a local patch-based CNN spatial feature extraction architecture [17,23,[25][26][27]. However, most of these methods improve network performance through spatial information, without considering the contribution difference of different spectra for classification result.…”

Section: Introductionmentioning

confidence: 99%

Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification

Han

Wang

Zhou

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Sea ice is one of the most prominent marine disasters in high latitudes. Remote sensing technology provides an effective means for sea ice detection. Remote sensing sea ice images contain rich spectral and spatial information. However, most traditional methods only focus on spectral information or spatial information, and do not excavate the feature of spectral and spatial simultaneously in remote sensing sea ice images classification. At the same time, the complex correlation characteristics among spectra and small sample problem in sea ice classification also limit the improvement of sea ice classification accuracy. For this issue, this paper proposes a new remote sensing sea ice image classification method based on squeeze-and-excitation (SE) network, convolutional neural network (CNN), and support vector machines (SVMs). The proposed method designs 3D-CNN deep network so as to fully exploit the spatial-spectrum features of remote sensing sea ice images and integrates SE-Block into 3D-CNN in-depth network in order to distinguish the contributions of different spectra to sea ice classification. According to the different contributions of spectral features, the weight of each spectral feature is optimized by fusing SE-Block in order to further enhance the sample quality. Finally, information-rich and representative samples are chosen by combining the idea of active learning and input into SVM classifier, and this achieves superior classification accuracy of remote sensing sea ice images with small samples. In order to verify the effectiveness of the proposed method, we conducted experiments on three different data from Baffin Bay, Bohai Bay, and Liaodong Bay. The experimental results show that compared with other classical classification methods, the proposed method comprehensively considers the correlation among spectral features and the small samples problems and deeply excavates the spatial-spectrum characteristics of sea ice and achieves better classification performance, which can be effectively applied to remote sensing sea ice image classification.

show abstract

Semi‐supervised classification of fundus images combined with CNN and GCN

Duan

Huang

Chen

et al. 2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose Diabetic retinopathy (DR) is one of the most serious complications of diabetes, which is a kind of fundus lesion with specific changes. Early diagnosis of DR can effectively reduce the visual damage caused by DR. Due to the variety and different morphology of DR lesions, automatic classification of fundus images in mass screening can greatly save clinicians' diagnosis time. To alleviate these problems, in this paper, we propose a novel framework—graph attentional convolutional neural network (GACNN). Methods and Materials The network consists of convolutional neural network (CNN) and graph convolutional network (GCN). The global and spatial features of fundus images are extracted by using CNN and GCN, and attention mechanism is introduced to enhance the adaptability of GCN to topology map. We adopt semi‐supervised method for classification, which greatly improves the generalization ability of the network. Results In order to verify the effectiveness of the network, we conducted comparative experiments and ablation experiments. We use confusion matrix, precision, recall, kappa score, and accuracy as evaluation indexes. With the increase of the labeling rates, the classification accuracy is higher. Particularly, when the labeling rate is set to 100%, the classification accuracy of GACNN reaches 93.35%. Compared with DenseNet121, the accuracy rate is improved by 6.24%. Conclusions Semi‐supervised classification based on attention mechanism can effectively improve the classification performance of the model, and attain preferable results in classification indexes such as accuracy and recall. GACNN provides a feasible classification scheme for fundus images, which effectively reduces the screening human resources.

show abstract

Semisupervised graph convolutional network for hyperspectral image classification

Cited by 24 publications

References 39 publications

Hyperspectral Image Classification with Localized Graph Convolutional Filtering

Hyperspectral Image Classification with Localized Graph Convolutional Filtering

Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification

Semi‐supervised classification of fundus images combined with CNN and GCN

Contact Info

Product

Resources

About