Multi-scale Network Research Articles

Multi-Scale Spatio-Temporal Attention Networks for Network-Scale Traffic Learning and Forecasting.

Accurate and timely forecasting of traffic on local road networks is crucial for deploying effective dynamic traffic control, advanced route planning, and navigation services. This task is particularly challenging due to complex spatio-temporal dependencies arising from non-Euclidean spatial relations in road networks and non-linear temporal dynamics influenced by changing road conditions. This paper introduces the spatio-temporal network embedding (STNE) model, a novel deep learning framework tailored for learning and forecasting graph-structured traffic data over extended input sequences. Unlike traditional convolutional neural networks (CNNs), the model employs graph convolutional networks (GCNs) to capture the spatial characteristics of local road network topologies. Moreover, the segmentation of very long input traffic data into multiple sub-sequences, based on significant temporal properties such as closeness, periodicity, and trend, is performed. Multi-dimensional long short-term memory neural networks (MDLSTM) are utilized to flexibly access multi-dimensional context. Experimental results demonstrate that the STNE model surpasses state-of-the-art traffic forecasting benchmarks on two large-scale real-world traffic datasets.

A new multi-modal time series transformation method and multi-scale convolutional attention network for railway wagon bearing fault diagnosis

To align with the evolving trends in intelligent railway wagon operation and maintenance and to enhance the precision of railway wagon bearing fault diagnosis, this paper introduces a novel method for bearing fault diagnosis. The method comprises two key innovations. Firstly, a multi-modal time series transformation method is proposed. This method extracts time series data from the original time domain signals via self-adaptive ensemble empirical mode decomposition with adaptive noise, transforms them into 2D matrices, and captures inter- and intra-period information relationships through convolution. Secondly, a multi-scale convolutional attention network is introduced, enriching fault information by utilizing parallel multi-scale convolution for down-sampling. To prevent feature loss, sliding convolution is adopted instead of pooling. Additionally, the model incorporates the convolutional block attention module to focus on critical information. Experimental validation conducted in a laboratory using a self-developed railway wagon bearing dynamic performance tester demonstrates high diagnostic accuracy and strong overall performance. The method’s generalizability is further confirmed through validation using publicly available datasets. This method could find practical use in railway maintenance, improving the accuracy of bearing fault diagnosis, and making operations more efficient.

Using the MSFNet Model to Explore the Temporal and Spatial Evolution of Crop Planting Area and Increase Its Contribution to the Application of UAV Remote Sensing

Remote sensing technology can be used to monitor changes in crop planting areas to guide agricultural production management and help achieve regional carbon neutrality. Agricultural UAV remote sensing technology is efficient, accurate, and flexible, which can quickly collect and transmit high-resolution data in real time to help precision agriculture management. It is widely used in crop monitoring, yield prediction, and irrigation management. However, the application of remote sensing technology faces challenges such as a high imbalance of land cover types, scarcity of labeled samples, and complex and changeable coverage types of long-term remote sensing images, which have brought great limitations to the monitoring of cultivated land cover changes. In order to solve the abovementioned problems, this paper proposed a multi-scale fusion network (MSFNet) model based on multi-scale input and feature fusion based on cultivated land time series images, and further combined MSFNet and Model Diagnostic Meta Learning (MAML) methods, using particle swarm optimization (PSO) to optimize the parameters of the neural network. The proposed method is applied to remote sensing of crops and tomatoes. The experimental results showed that the average accuracy, F1-score, and average IoU of the MSFNet model optimized by PSO + MAML (PSML) were 94.902%, 91.901%, and 90.557%, respectively. Compared with other schemes such as U-Net, PSPNet, and DeepLabv3+, this method has a better effect in solving the problem of complex ground objects and the scarcity of remote sensing image samples and provides technical support for the application of subsequent agricultural UAV remote sensing technology. The study found that the change in different crop planting areas was closely related to different climatic conditions and regional policies, which helps to guide the management of cultivated land use and provides technical support for the realization of regional carbon neutrality.

Stepwise Attention-Guided Multiscale Fusion Network for Lightweight and High-Accurate SAR Ship Detection

Many exceptional deep learning networks have demonstrated remarkable proficiency in general object detection tasks. However, the challenge of detecting ships in synthetic aperture radar (SAR) imagery increases due to the complex and various nature of these scenes. Moreover, sophisticated large-scale models necessitate substantial computational resources and hardware expenses. To address these issues, a new framework is proposed called a stepwise attention-guided multiscale feature fusion network (SAFN). Specifically, we introduce a stepwise attention mechanism designed to selectively emphasize relevant information and filter out irrelevant details of objects in a step-by-step manner. Firstly, a novel LGA-FasterNet is proposed, which incorporates a lightweight backbone FasterNet with lightweight global attention (LGA) to realize expressive feature extraction while reducing the model’s parameters. To effectively mitigate the impact of scale and complex background variations, a deformable attention bidirectional fusion network (DA-BFNet) is proposed, which introduces a novel deformable location attention (DLA) block and a novel deformable recognition attention (DRA) block, strategically integrating through bidirectional connections to achieve enhanced features fusion. Finally, we have substantiated the robustness of the new framework through extensive testing on the publicly accessible SAR datasets, HRSID and SSDD. The experimental outcomes demonstrate the competitive performance of our approach, showing a significant enhancement in ship detection accuracy compared to some state-of-the-art methods.

Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

Language conditioned multi-scale visual attention networks for visual grounding

Visual grounding (VG) is a task that requires to locate a specific region in an image according to a natural language expression. Existing efforts on the VG task are divided into two-stage, one-stage and Transformer-based methods, which have achieved high performance. However, most of the previous methods extract visual information at a single spatial scale and ignore visual information at other spatial scales, which makes these models unable to fully utilize the visual information. Moreover, the insufficient utilization of linguistic information, especially failure to capture global linguistic information, may lead to failure to fully understand language expressions, thus limiting the performance of these models. To better address the task, we propose a language conditioned multi-scale visual attention network (LMSVA) for visual grounding, which can sufficiently utilize visual and linguistic information to perform multimodal reasoning, thus improving performance of model. Specifically, we design a visual feature extractor containing a multi-scale layer to get the required multi-scale visual features by expanding the original backbone. Moreover, we exploit pooling the output of the pre-trained Bidirectional Encoder Representations from Transformers (BERT) model to extract sentence-level linguistic features, which can enable the model to capture global linguistic information. Inspired by the Transformer architecture, we present the Visual Attention Layer guided by Language and Multi-Scale Visual Features (VALMS), which is able to better learn the visual context guided by multi-scale visual and linguistic features, and facilitates further multimodal reasoning. Extensive experiments on four large benchmark datasets, including ReferItGame, RefCOCO, RefCOCO+ and RefCOCOg, demonstrate that our proposed model achieves the state-of-the-art performance.

MFCF-Gait: Small Silhouette-Sensitive Gait Recognition Algorithm Based on Multi-Scale Feature Cross-Fusion.

Gait recognition based on gait silhouette profiles is currently a major approach in the field of gait recognition. In previous studies, models typically used gait silhouette images sized at 64 × 64 pixels as input data. However, in practical applications, cases may arise where silhouette images are smaller than 64 × 64, leading to a loss in detail information and significantly affecting model accuracy. To address these challenges, we propose a gait recognition system named Multi-scale Feature Cross-Fusion Gait (MFCF-Gait). At the input stage of the model, we employ super-resolution algorithms to preprocess the data. During this process, we observed that different super-resolution algorithms applied to larger silhouette images also affect training outcomes. Improved super-resolution algorithms contribute to enhancing model performance. In terms of model architecture, we introduce a multi-scale feature cross-fusion network model. By integrating low-level feature information from higher-resolution images with high-level feature information from lower-resolution images, the model emphasizes smaller-scale details, thereby improving recognition accuracy for smaller silhouette images. The experimental results on the CASIA-B dataset demonstrate significant improvements. On 64 × 64 silhouette images, the accuracies for NM, BG, and CL states reached 96.49%, 91.42%, and 78.24%, respectively. On 32 × 32 silhouette images, the accuracies were 94.23%, 87.68%, and 71.57%, respectively, showing notable enhancements.

3D Positioning of Drones through Images.

Drones traditionally rely on satellite signals for positioning and altitude. However, when in a special denial environment, satellite communication is interrupted, and the traditional positioning and height determination methods face challenges. We made a dataset at the height of 80-200 m and proposed a multi-scale input network. The positioning index RDS achieved 76.3 points, and the positioning accuracy within 20 m was 81.7%. This paper proposes a method to judge the height by image alone, without the support of other sensor data. One height judgment can be made per single image. Based on the UAV image-satellite image matching positioning technology, by calculating the actual area represented by the UAV image in real space, combined with the fixed parameters of the optical camera, the actual height of the UAV flight is calculated, which is 80-200 m, and the relative error rate of height is 18.1%.

Neuron-astrocyte interaction-inspired percolative networks with metal microdendrites and nanostars for ultrasensitive and transparent electronic skins

Biological systems provide innovative designs for electronic devices, optimizing network configurations for high-performance signal transmission with minimal energy consumption. The brain, as one of the most complex biological structures, demonstrates efficient network design through the multiscale radial networks of neurons and astrocytes. Emulating these brain networks offers a blueprint for the development of ultrasensitive pressure sensors for electronic skin, aiming to provide a more intuitive and sensitive mode of interaction between humans and machines. Herein, we propose a neuromorphic percolative network inspired by neuron-astrocyte interactions for ultrasensitive pressure sensors employing metal microdendrites and nanostars. Electromechanical investigation through representative volume elements simulation reveals that the optimized arrangement of microdendrites and nanostars in the neuromorphic percolative system enhances the percolation threshold and probability. Following these simulation results, we developed a neuromorphic percolative polyurethane (NP-PU) matrix utilizing the metal microdendrite-nanostar networks. The augmented quantum tunneling effect in the NP-PU matrix was investigated through electrochemical impedance spectroscopy and capacitance analysis. The fabricated piezoresistive pressure sensor with the NP-PU matrix shows ultrahigh sensitivity (160.3 kPa−1) at a low pressure range and a low limit of detection resolution (4 Pa), enabled by multi-channel quantum tunneling in the metal particle networks. Furthermore, the sensor maintains excellent mechanical flexibility and high optical transparency (75.4 %), improving its efficacy in applications like electronic skin and force touch panel. Our study highlights the potential of leveraging biological system-inspired network designs for crafting advanced electronic devices.

A diffusion model multi-scale feature fusion network for imbalanced medical image classification research

Background and objectiveMedicine image classification are important methods of traditional medical image analysis, but the trainable data in medical image classification is highly imbalanced and the accuracy of medical image classification models is low. In view of the above two common problems in medical image classification. This study aims to: (i) effectively solve the problem of poor training effect caused by the imbalance of class imbalanced data sets. (ii) propose a network framework suitable for improving medical image classification results, which needs to be superior to existing methods. MethodsIn this paper, we put in the diffusion model multi-scale feature fusion network (DMSFF), which mainly uses the diffusion generation model to overcome imbalanced classes (DMOIC) on highly imbalanced medical image datasets. At the same time, it is processed according to the cropped image augmentation strategy through cropping (IASTC). Based on this, we use the new dataset to design a multi-scale feature fusion network (MSFF) that can fully utilize multiple hierarchical features. The DMSFF network can effectively solve the problems of small and imbalanced samples and low accuracy in medical image classification. ResultsWe evaluated the performance of the DMSFF network on highly imbalanced medical image classification datasets APTOS2019 and ISIC2018. Compared with other classification models, our proposed DMSFF network achieved significant improvements in classification accuracy and F1 score on two datasets, reaching 0.872, 0.731, and 0.906, 0.836, respectively. ConclusionsOur newly proposed DMSFF architecture outperforms existing methods on two datasets, and verifies the effectiveness of generative model inverse balance for imbalance class datasets and feature enhancement by multi-scale feature fusion. Further, the method can be applied to other class imbalanced data sets where the results will be improved.

State of Health Estimations for Lithium-Ion Batteries Based on MSCNN

Lithium-ion batteries, essential components in new energy vehicles and energy storage stations, play a crucial role in health-status investigation and ensuring safe operation. To address challenges such as limited estimation accuracy and a weak generalization ability in conventional battery state of health (SOH) estimation methods, this study presents an integrated approach for SOH estimation that incorporates multiple health indicators and utilizes the multi-scale convolutional neural network (MSCNN) model. Initially, the aging characteristics of the battery are comprehensively analyzed, and then the health indicators are extracted from the charging data, including the temperature, time, current, voltage, etc., and the statistical transformation is performed. Subsequently, Pearson’s method is employed to analyze the correlation between these health indicators and identify those with strong correlations. A regression-prediction model based on the MSCNN model is then developed for estimating battery SOH. Finally, validation using a publicly available lithium-ion battery dataset demonstrates that, under similar operating conditions, the mean absolute error (MAE) for SOH estimation is less than 0.67%, the mean absolute percentage error (MAPE) is less than 0.37%, and the root mean square error (RMSE) is less than 0.74%. The MSCNN has good generalization for datasets with different working conditions.

Multi-Scale Spatial-Temporal Attention Networks for Functional Connectome Classification.

Many neuropsychiatric disorders are considered to be associated with abnormalities in the functional connectivity networks of the brain. The research on the classification of functional connectivity can therefore provide new perspectives for understanding the pathology of disorders and contribute to early diagnosis and treatment. Functional connectivity exhibits a nature of dynamically changing over time, however, the majority of existing methods are unable to collectively reveal the spatial topology and time-varying characteristics. Furthermore, despite the efforts of limited spatial-temporal studies to capture rich information across different spatial scales, they have not delved into the temporal characteristics among different scales. To address above issues, we propose a novel Multi-Scale Spatial-Temporal Attention Networks (MSSTAN) to exploit the multi-scale spatial-temporal information provided by functional connectome for classification. To fully extract spatial features of brain regions, we propose a Topology Enhanced Graph Transformer module to guide the attention calculations in the learning of spatial features by incorporating topology priors. A Multi-Scale Pooling Strategy is introduced to obtain representations of brain connectome at various scales. Considering the temporal dynamic characteristics between dynamic functional connectome, we employ Locality Sensitive Hashing attention to further capture long-term dependencies in time dynamics across multiple scales and reduce the computational complexity of the original attention mechanism. Experiments on three brain fMRI datasets of MDD and ASD demonstrate the superiority of our proposed approach. In addition, benefiting from the attention mechanism in Transformer, our results are interpretable, which can contribute to the discovery of biomarkers. The code is available at https://github.com/LIST-KONG/MSSTAN.

DeepFake detection method based on multi-scale interactive dual-stream network

DeepFake face forgery has a serious negative impact on both society and individuals. Therefore, research on DeepFake detection technologies is necessary. At present, DeepFake detection technology based on deep learning has achieved acceptable results on high-quality datasets; however, its detection performance on low-quality datasets and cross-datasets remains poor. To address this problem, this paper presents a multi-scale interactive dual-stream network (MSIDSnet). The network is divided into spatial- and frequency-domain streams and uses a multi-scale fusion module to capture both the facial features of images that have been manipulated in the spatial domain under different circumstances and the fine-grained high-frequency noise information of forged images. The network fully integrates the features of the spatial- and frequency-domain streams through an interactive dual-stream module and uses vision transformer (ViT) to further learn the global information of the forged facial features for classification. Experimental results confirm that the accuracy of this method reached 99.30 % on the high-quality dataset Celeb-DF-v2, and 95.51 % on the low-quality dataset FaceForensics++. Moreover, the results of the cross-dataset experiments were superior to those of the other comparison methods.

Spatiotemporal prediction of surface roughness evolution of C/C composites based on recurrent neural network

Carbon/carbon (C/C) composites are widely used in aerospace applications due to their excellent properties. Their surface roughness is an important factor affecting the material properties and ablation resistance, which is essential for the accurate prediction of the material. Images are often used to summarize and characterize microstructural features, which include information such as fiber microstructure and fiber orientations. An ablation shape evolution model based on optimization of attention mechanism, which combines multi-scale convolutional neural network (MSCNN) and long short-term memory (LSTM) methods for the C/C composites, is proposed. MSCNN encodes the microstructural information of the ablation image, which is fed into the LSTM model to extract the spatiotemporal features and long-term dependencies latent in the temporal law. The attention mechanism is used to assign different weights to the extracted features which makes the model focus more on the important time steps in the sequence. The results show that the proposed model achieves excellent effects in predicting the evolution of ablative morphology, with high agreement with the simulated values. The method saves time and cost, while providing an efficient and reliable method for the design and optimization of thermal protection materials.

An intrusion detection method combining variational auto-encoder and generative adversarial networks

Deep learning is a crucial research area in network security, particularly when it comes to detecting network attacks. While some deep learning algorithms have shown promising results in distinguishing between normal and abnormal traffic, identifying different types of imbalanced anomalous traffic data is still a challenging task at present. To enhance the detection performance of unbalanced anomalous flows, we propose a new intrusion detection architecture based on a variational auto-encoder (VAE) and generative adversarial networks (GAN) in this research. Firstly, we present the VAE-WGAN model, which combines the advantages of VAE and GAN and enables us to generate data with predefined labels to balance the original training dataset. In the intrusion detection phase, we use a hybrid neural network model based on stacked Long Short-Term Memory (LSTM) and Multi-Scale Convolutional Neural Network (MSCNN). Stacked LSTM and MSCNN networks can extract network characteristics at different depths and scales, and subsequent feature fusion is used to increase network attack detection rates. Finally, the results from the NSL-KDD and AWID datasets indicate that the proposed network intrusion detection model improves the accuracy of network attack detection. The model outperforms other existing intrusion detection approaches in terms of accuracy, precision, recall, and f1-score, obtaining 83.45% accuracy and 83.69% f1-score on the NSL-KDD dataset. Moreover, it attains an accuracy and f1-score exceeding 98.9% on the AWID dataset.

Predicting Signal Reception Information from GNSS Satellites in Indoor Environments without Site Survey: Towards Opportunistic Indoor Positioning Based on GNSS Fingerprinting

While traditional GPS localization is impractical in certain indoor environments, GPS satellites offer a valuable source of indoor contextual information, particularly around window-side areas where signals are more accessible. This study introduces a new method that predicts GPS signal reception information in a target indoor environment without the need for actual data collection in the target environment. By predicting the strengths of GPS signals that are expected to be measured at various indoor positions, we can construct a GPS signal reception map of a target environment, which functions similarly to a Wi-Fi fingerprinting map surrounding window-side areas, offering a new dimension in indoor positioning systems. For instance, it aids in the correction of accumulated errors in pedestrian dead reckoning (PDR) systems. Our proposed method leverages easily accessible inputs, including satellite location data, indoor floorplan image of the target floor, and 3D mapping of the surrounding buildings, to predict signal reception at each position in the target environment. We developed a specialized neural network, named multi-scale branch fusion network (MSBF-Net), designed to process and integrate data of varying scales, such as the floorplan image of the target environment and 3D map of the surrounding area obtained from Google Earth, with a specific focus on understanding the line-of-sight (LOS) and multi-path effects caused by internal obstacles and surrounding buildings. This advanced capability enables the network to effectively interpret complex signal interactions within urban environments, enhancing its predictive accuracy for GPS signal reception. The effectiveness of our method was rigorously evaluated using real-world environments. In addition, we employed our method to implement opportunistic GPS fingerprint-based indoor positioning, where position estimates are provided when a strong signal is observed from at least one satellite. Surprisingly, the positioning method achieved a positioning error of only 2.8 meters when a smartphone is close to window-side areas even though the method does not rely on labeled training data collected in a target environment and signal infrastructures installed in the target environment.

Skeleton-guided multi-scale dual-coordinate attention aggregation network for retinal blood vessel segmentation

Deep learning plays a pivotal role in retinal blood vessel segmentation for medical diagnosis. Despite their significant efficacy, these techniques face two major challenges. Firstly, they often neglect the severe class imbalance in fundus images, where thin vessels in the foreground are proportionally minimal. Secondly, they are susceptible to poor image quality and blurred vessel edges, resulting in discontinuities or breaks in vascular structures. In response, this paper proposes the Skeleton-guided Multi-scale Dual-coordinate Attention Aggregation (SMDAA) network for retinal vessel segmentation. SMDAA comprises three innovative modules: Dual-coordinate Attention (DCA), Unbalanced Pixel Amplifier (UPA), and Vessel Skeleton Guidance (VSG). DCA, integrating Multi-scale Coordinate Feature Aggregation (MCFA) and Scale Coordinate Attention Decoding (SCAD), meticulously analyzes vessel structures across various scales, adept at capturing intricate details, thereby significantly enhancing segmentation accuracy. To address class imbalance, we introduce UPA, dynamically allocating more attention to misclassified pixels, ensuring precise extraction of thin and small blood vessels. Moreover, to preserve vessel structure continuity, we integrate vessel anatomy and develop the VSG module to connect fragmented vessel segments. Additionally, a Feature-level Contrast (FCL) loss is introduced to capture subtle nuances within the same category, enhancing the fidelity of retinal blood vessel segmentation. Extensive experiments on three public datasets (DRIVE, STARE, and CHASE_DB1) demonstrate superior performance in comparison to current methods. The code is available at https://github.com/wangwxr/SMDAA_NET.

Optimized Adaptive Multi-Scale Dual An for Multi-Objective CHS and Energy-Aware Routing in 6G WC

In this research work, an Adaptive Multi-Scale Dual Attention Network with ZOA for Multi-Objective CHS with energy-aware routing in 6G wireless Communication (CHS-EAR-AM-SDAN-6G) is proposed to secure the data transmission by selecting optimum cluster heads in the 6G Wireless Communication network. Initially, the nodes are gathered together to form a cluster using an Adaptive Multi-Scale Dual Attention Network (AM-SDAN). The Zebra Optimization Algorithm (ZOA) strategically selects Cluster Heads (CHs) in wireless networks based on a multi-objective fitness function (MoFF) that minimizes energy consumption while considering factors, like distance, delay, and traffic density. The path and minimum value of fitness are recognized as the routing path and statistics are promoted to the sink node through the cluster head. The proposed scheme has been applied in Python and productivity of the proposed method is predictable with the help of several performances they are energy consumption, detection rate, computational time, packet delivery rate, number of alive nodes, and security. The performance of the proposed CHS-EAR-AMSDAN-6G method attains 25.93%, 24.81%, and 23.38% of alive nodes, 24.45%, 26.71% and 21.32% lower packet delivery rate, 27.56%, 26.43%, and 28.61% low computational period, related with three current methods, such as Generative Adversarial Learning for ITM in 6G Wireless Communication Networks (CHS-EAR-GAL-ITM-6G), ML Algorithms for the Future 6G WCN (CHS-EAR-ML-6G), Energy Efficient Distributed Federated Learning to the 6G Wireless Communication Networks (CHS-EAR-EEDFL-6G), respectively.

Learning the feature distribution similarities for online time series anomaly detection

Identifying anomalies in multi-dimensional sequential data is crucial for ensuring optimal performance across various domains and in large-scale systems. Traditional contrastive methods utilize feature similarity between different features extracted from multidimensional raw inputs as an indicator of anomaly severity. However, the complex objective functions and meticulously designed modules of these methods often lead to efficiency issues and a lack of interpretability. Our study introduces a structural framework called SimDetector, which is a Local–Global Multi-Scale Similarity Contrast network. Specifically, the restructured and enhanced GRU module extracts more generalized local features, including long-term cyclical trends. The multi-scale sparse attention module efficiently extracts multi-scale global features with pattern information. Additionally, we modified the KL divergence to suit the characteristics of time series anomaly detection, proposing a symmetric absolute KL divergence that focuses more on overall distribution differences. The proposed method achieves results that surpass or approach the State-of-the-Art (SOTA) on multiple real-world datasets and synthetic datasets, while also significantly reducing Multiply-Accumulate Operations (MACs) and memory usage.

A multiscale dilated attention network for hyperspectral image classification

Hyperspectral imaging is an image obtained by combining spectral detection technology and imaging technology, which can collect electromagnetic spectra in the wavelength range of visible light to near-infrared. It is an important research content in the field of ground observation in hyperspectral remote sensing. However, hyperspectral image face significant challenges in classification task due to their high spectral dimensions, lack of labeled samples, and strong correlation between bands. In order to fully extract features from both spectral and spatial dimensions and improve classification accuracy in the case of limited training samples, a multiscale dilated attention network is proposed for hyperspectral image classification. First, a three-dimensional convolutional layer is used to extract the shallow features of the image. Then, a multiscale dilated attention module is proposed by combining dilated convolution and channel attention. Using ordinary convolution and dilated convolution to form different receptive fields. Channel attention is used to remodel the obtained multiscale features, enhancing the inter-channel correlation. After that, a multiscale spatial-spectral attention module is constructed using multiple asymmetric convolutions to obtain spatial and spectral attention features at different positions, further enhancing important feature suppression over non-important features. Finally, using softmax to classify the obtained features. Using Indian Pines, Pavia University, KSC and University of Houston as experimental datasets, the overall classification accuracy of this paper’s method achieved 98.97%, 99.14%, 99.45%, and 98.56% respectively, using only 5%, 1%, 10%, and 10% of training samples per class. Compared with seven advanced classification methods, the experimental results show that the proposed method can achieve the highest classification accuracy with limited training samples.