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

The classification of hyperspectral remote sensing images (HSI) is an important task in the processing and application of hyperspectral images. Convolutional neural network (CNN) has significant advantages in the extraction and fusion of hyperspectral image spectrum and spatial features, so it has become a common method in the field of HSI classification. However, the spectral domain feature redundancy of hyperspectral images is very high, and the spatial domain feature structure is complex, which makes CNN more time-consuming and higher memory requirements in the feature extraction process. Based on this problem, lightweight networks with fewer parameters have gradually become the main application method in the field of HSI classification. In order to reduce the computational complexity of deep feature extraction and take into account the shallow features, a high-order nonlinear Ghost module is proposed on the basis of the original Ghost linear transformation module. Furthermore, in view of the independent characteristics of each dimension of HSI, a Trip-GhostNet is proposed, which simultaneously extracts and fuses features from three dimensions in a lightweight manner. According to the distribution characteristics of HSI, the influence of attention embedding methods in the high-order Ghost module of each branch on the feature extraction is compared and analyzed. The results show that the proposed model can reduce model calculations and improve classification accuracy, and is suitable for HSI classification problems.

The extraction of concise and discriminative features from hyperspectral remote sensing images (HSIs) holds great significance for land cover classification tasks. Nevertheless, the intricate spatial-spectral tensor structure and inaccurate class labels undermine the performance of existing vector-based or Tucker tensor-based feature dimensionality reduction (DR) approaches. To tackle this problem, we propose an Adaptive Tensor-Ring Manifold Maintaining Embedding (ATRMME) approach for HSI feature DR in the presence of noisy labels. Firstly, a tensor-ring subspace representation theory is established to characterize the low-dimensional hyperspectral tensor subspace. To mine concise features from complex spatial-spectral data, differing from existing Tucker-based DR methods that involve exorbitant parameter overheads, a nuclear norm-constrained Tensor-Ring (TR) feature representation term is designed. This term enables the compression of key features within the low-dimensional subspace with a linear parameter cost. For the adaptive perception and capture of the manifold structure under noisy labels, an adaptive adjacency matrix is constructed, and the adjacency relationships are reorganized based on the TR feature distribution. To guarantee the effective execution of model training, an alternating optimization algorithm is developed for parameter estimation. Experimental results on multiple hyperspectral datasets verify that the ATRMME approach exhibits strong robustness against noisy labels, outperforms conventional vector-based and Tucker tensor-based methods, and has lower parameter requirements.

Hyperspectral remote sensing (HRS) image classification is time-consuming and complex due to its wide spectral range and large number of samples. Factors such as heterogeneous behaviour, unbalanced class distributions, complex boundaries, multiple spectral bands, inconsistent samples, significant spatial variability, and interclass similarities further challenge image classification. The design of a robust classification model that addresses these challenges demands efficient pre-processing of input information, e.g., dimensionality reduction and representative feature extraction, with the ability to handle information uncertainty and to reduce computational complexity. In line with these objectives, we have proposed a classification model called FRELM-SAE, which utilises fuzzy granulation of input features, a rule-based extreme learning machine (ELM), and a stacked autoencoder (SAE). Fuzzy granulation and rule-based ELM address the generalisation aspects and the complexity of the decision-making process. The SAE reduces the noise from the input feature space and performs representative feature extraction. Various experiments demonstrate the proposed model’s performance in classifying two HRS images. The experimental results show its supremacy over related work across performance metrics, including overall accuracy, precision, recall, etc.

Traditional remote sensing image surveys rely on field observations, which have shortcomings such as low efficiency and limited coverage, making it difficult to meet the needs of urban planning and management. In response to this, this article conducts in-depth research on remote sensing image classification methods based on graph neural networks (GNN). This study adopts a joint framework of GAT (Graph Attention Network)+SLC (Simple Linear Iterative Clustering)+Hybrid Pooling. Use SLIC algorithm to perform superpixel segmentation on hyperspectral data and construct a graph structure that integrates spectral spatial features. Utilizing GAT's attention mechanism to enhance feature interaction among neighboring nodes, combined with a hybrid pooling strategy to balance feature dimensionality reduction and key information preservation. The experiment was conducted on the public datasets WHU-RS19 and UC Merced, using traditional CNN, random forest, and minimum distance methods as baseline models. The significance of the differences was verified through independent sample t-test. By expanding the sample coverage, optimizing the model regularization strategy, and continuously iterating training, the generalization performance of the model has been significantly improved. Therefore, from the comparison of classification performance, graph NN classification is superior to minimum distance classification. This method utilizes perspective remote sensing data to achieve accurate ground target classification and dynamic change information extraction, providing reliable data support for urban land survey and management.

Graph neural networks (GNNs) is an information - processing system that uses message passing among graph nodes. In recent years, GNN variants including graph attention network (GAT), graph convolutional network (GCN), and graph recurrent network (GRN) have shown revolutionary performance in computer vision applications using deep learning and artificial intelligence. These neural network model extensions, collect information in the form of graphs. GNN may be divided into three groups based on the challenges it solves: link prediction, node classification, graph classification. Machines can differentiate and recognise objects in image and video using standard CNNs. Extensive amount of research work needs to be done before robots can have same visual intuition as humans. GNN architectures, on the other hand, may be used to solve various image categorization and video challenges. The number of GNN applications in computer vision not limited, continues to expand. Human-object interaction, actin understanding, image categorization from a few shots and many more. In this paper use of GNN in image and video understanding, design aspects, architecture, applications and implementation challenges towards computer vision is described. GNN is a strong tool for analysing graph data and is still a relatively active area that needs further researches attention to solve many computer vision applications.

The graph neural network (GNN) has recently become an emerging research topic for processing non-euclidean data structures since the data used in various popular application domains are usually modeled as a graph, such as social networks, recommendation systems, and computer vision. Previous GNN accelerators commonly utilize the hybrid architecture to resolve the issue of “hybrid computing pattern” in GNN training. Nevertheless, the hybrid architecture suffers from poor utilization of hardware resources mainly due to the dynamic workloads between different phases in GNN. To address these issues, existing GNN accelerators adopt a unified structure with numerous processing elements and high bandwidth memory. However, the large amount of data movement between the processor and memory could heavily downgrade the performance of such accelerators in real-world graphs. As a result, the processing-in-memory architecture, such as the ReRAM-based crossbar, becomes a promising solution to reduce the memory overhead of GNN training. In this work, we present the TCAM-GNN, a novel TCAM-based data processing strategy, to enable high-throughput and energy-efficient GNN training over ReRAM-based crossbar architecture. Several hardware co-designed data structures and placement methods are proposed to fully exploit the parallelism in GNN during training. In addition, we propose a dynamic fixed-point formatting approach to resolve the precision issue. An adaptive data reusing policy is also proposed to enhance the data locality of graph features by the bootstrapping batch sampling approach. Overall, TCAM-GNN could enhance computing performance by 4.25× and energy efficiency by 9.11× on average compared to the neural network accelerators.

<strong class="journal-contentHeaderColor">Abstract.</strong> Hyperspectral images contain abundant spectral and spatial information about the earth's surface, labeling data processing and analysis more difficult, as well as the problem of sample labeling. In this paper, local binary pattern (LBP), sparse representation and mixed logistic regression model are introduced, and a sample labeling method based on neighborhood information and priority classifier discrimination is presented. Then, a hyperspectral remote sensing image classification method based on texture features and semi-supervised learning is implemented. The LBP is employed to extract features of spatial texture information from remote sensing images and enrich the feature information of samples. Then the multivariate logistic regression model is used to select the unlabeled samples with the largest amount of information, and the unlabeled samples with neighborhood information and priority classifier tags are selected to obtain the pseudo-labeled samples after learning. By making full use of the advantages of sparse representation and mixed logistic regression model, a new hyperspectral remote sensing image classification model based on semi-supervised learning is constructed to effectively achieve accurate classification of hyperspectral images. The data of Indian Pines, Salinas scene and Pavia University are selected to verify the validity of the proposed method. The experiment results show that the proposed classification method can obtain higher classification accuracy and show stronger timeliness and generalization ability.

Deep learning on graphs is an upcoming area of study. This chapter provides an introduction to graph neural networks (GNNs), a type of neural network that is designed to process data represented in the form of graphs. First, it summarizes the explanation of deep learning on graphs. The fundamental concepts of graph neural networks, as well as GNN theories, are then explained. In this chapter, different types of graph neural network (GNN) are also explained. At the end, the applications of graph neural network where GNN is used and for what purpose it is going to be used are explained. This also explores the various applications of GNNs in fields such as social network analysis, recommendation systems, drug discovery, computer vision, and natural language processing. With the increasing prevalence of graph data, GNNs are becoming increasingly important and will likely continue to play a significant role in many fields in the future.

Sex classification is a major benchmark of previous work in learning on the structural connectome, a naturally occurring brain graph that has proven useful for studying cognitive function and impairment. While graph neural networks (GNNs), specifically graph convolutional networks (GCNs), have gained popularity lately for their effectiveness in learning on graph data, achieving strong performance in adult sex classification tasks, their application to pediatric populations remains unexplored. We seek to characterize the capacity for GNN models to learn connectomic patterns on pediatric data through an exploration of training techniques and architectural design choices. Two datasets comprising an adult BRIGHT dataset (N = 147 Hodgkin's lymphoma survivors and N = 162 age similar controls) and a pediatric Human Connectome Project in Development (HCP-D) dataset (N = 135 healthy subjects) were utilized. Two GNN models (GCN simple and GCN residual), a deep neural network (multi-layer perceptron), and two standard machine learning models (random forest and support vector machine) were trained. Architecture exploration experiments were conducted to evaluate the impact of network depth, pooling techniques, and skip connections on the ability of GNN models to capture connectomic patterns. Models were assessed across a range of metrics including accuracy, AUC score, and adversarial robustness. GNNs outperformed other models across both populations. Notably, adult GNN models achieved 85.1% accuracy in sex classification on unseen adult participants, consistent with prior studies. The extension of the adult models to the pediatric dataset and training on the smaller pediatric dataset were sub-optimal in their performance. Using adult data to augment pediatric models, the best GNN achieved comparable accuracy across unseen pediatric (83.0%) and adult (81.3%) participants. Adversarial sensitivity experiments showed that the simple GCN remained the most robust to perturbations, followed by the multi-layer perceptron and the residual GCN. These findings underscore the potential of GNNs in advancing our understanding of sex-specific neurological development and disorders and highlight the importance of data augmentation in overcoming challenges associated with small pediatric datasets. Further, they highlight relevant tradeoffs in the design landscape of connectomic GNNs. For example, while the simpler GNN model tested exhibits marginally worse accuracy and AUC scores in comparison to the more complex residual GNN, it demonstrates a higher degree of adversarial robustness.

Hyperspectral remote sensing image classification based on residual generative Adversarial Neural Networks

To effectively utilize the rich spectral information of hyperspectral remote sensing images (HRSIs), the fractional Fourier transform (FRFT) feature of HRSIs is proposed to reflect the time-domain and frequency-domain characteristics of a spectral pixel simultaneously, and an FRFT order selection criterion is also proposed based on maximizing separability. Firstly, FRFT is applied to the spectral pixels, and the amplitude spectrum is taken as the FRFT feature of HRSIs. The FRFT feature is mixed with the pixel spectral to form the presented spectral and fractional Fourier transform mixed feature (SF2MF), which contains time–frequency mixing information and spectral information of pixels. K-nearest neighbor, logistic regression, and random forest classifiers are used to verify the superiority of the proposed feature. A 1-dimensional convolutional neural network (1D-CNN) and a two-branch CNN network (Two-CNNSF2MF-Spa) are designed to extract the depth SF2MF feature and the SF2MF-spatial joint feature, respectively. Moreover, to compensate for the defect that CNN cannot effectively capture the long-range features of spectral pixels, a long short-term memory (LSTM) network is introduced to be combined with CNN to form a two-branch network C-CLSTMSF2MF for extracting deeper and more efficient fusion features. A 3D-CNNSF2MF model is designed, which firstly performs the principal component analysis on the spa-SF2MF cube containing spatial information and then feeds it into the 3-dimensional convolutional neural network 3D-CNNSF2MF to extract the SF2MF-spatial joint feature effectively. The experimental results of three real HRSIs show that the presented mixed feature SF2MF can effectively improve classification accuracy.

Motif-aware curriculum learning for node classification.

The emergence of deep learning has not only brought great changes in the field of image recognition, but also achieved excellent node classification performance in graph neural networks. However, the existing graph neural network framework often uses methods based on spatial domain or spectral domain to capture network structure features. This process captures the local structural characteristics of graph data, and the convolution process has a large amount of calculation. It is necessary to use multi-channel or deep neural network structure to achieve the goal of modeling the high-order structural characteristics of the network. Therefore, this paper proposes a linear graph neural network framework [Linear Graph Neural Network (LGNN)] with superior performance. The model first preprocesses the input graph, and uses symmetric normalization and feature normalization to remove deviations in the structure and features. Then, by designing a high-order adjacency matrix propagation mechanism, LGNN enables nodes to iteratively aggregate and learn the feature information of high-order neighbors. After obtaining the node representation of the network structure, LGNN uses a simple linear mapping to maintain computational efficiency and obtain the final node representation. The experimental results show that the performance of the LGNN algorithm in some tasks is slightly worse than that of the existing mainstream graph neural network algorithms, but it shows or exceeds the machine learning performance of the existing algorithms in most graph neural network performance evaluation tasks, especially on sparse networks.

Graph neural networks induced by concept lattices for classification

In node classification, traditional graph neural networks (GNNs) typically assume implicit homophily, indicating that intraclass nodes are likely connected. However, real-world graphs frequently exhibit heterophily, in which interclass nodes are also commonly connected. To address this challenge, recent methods have adopted approaches such as expanding local neighborhoods and employing adaptive message aggregation to enhance the GNN performance on heterophily graphs. Nevertheless, these methods are restricted by the homophily assumption and fail to effectively capture long-range dependencies (e.g., widely separated intraclass nodes) and insufficiently leverage the graph topology. This study investigates the performance differences of GNN when it is applied to both homophily and heterophily graphs and finds that the distinguishability of neighborhood label distributions (NLDs) exhibits a significant correlation with the accuracy of node classification. To assess the impact of NLD on node classification, this study proposes a novel homophily metric based on node distinguishability. Subsequently, this study introduces a new GNN model named NLD-based GNN (NLDGNN) for node classification. First, NLDGNN initializes node representations by integrating node features with node NLDs. To address long-range dependencies in heterophily graphs, NLDGNN utilizes the global label relationship matrix with low-rank characteristics for global message passing. By combining the attention scores derived from the initial node representations, NLDGNN constructs the global label relationship matrix for enhanced message passing, thereby improving the expressiveness of node representations. Experimental results indicate that NLDGNN outperforms existing GNN models on both real-world homophily and heterophily graphs. The code of this study is available at https://github.com/wanli6/NLDGNN.