Feature Representation Ability Research Articles

EMAT: Efficient feature fusion network for visual tracking via optimized multi-head attention

The tracking methods based on Transformer have shown great potential in visual tracking and achieved significant tracking performance. The traditional transformer based feature fusion network divides a whole feature map into multiple image patches as its inputs, and then directly processes them in parallel, which will occupy a lot of computing resources and affect the computing efficiency of multi-head attention. In this paper, we design a novel feature fusion network with optimized multi-head attention in encoder and decoder architecture based on Transformer. The designed feature fusion network preprocess the input features and change the calculations of multi-head attention by using both the efficient multi-head self-attention module and efficient multi-head spatial reduction attention module. The two modules can reduce the influence of irrelevant background information, enhance the representation ability of template features and search region features, and greatly reduce the computational complexity. We propose a novel Transformer tracking method (named EMAT) based on the designed feature fusion network. The proposed EMAT is evaluated on seven challenging tracking benchmarks to demonstrate its superiority, including LaSOT, GOT-10k, TrackingNet, UAV123, VOT2018, NfS and VOT-RGBT2019. The proposed tracker achieves well tracking performance, and obtains precision score of 89.0% on UAV123, AUC score of 64.6% on LaSOT, EAO score of 34.8% on VOT-RGBT2019, which outperforms most advanced trackers. EMAT runs at a real-time speed of about 35 FPS during tracking.

Deep convolutional dictionary learning network for sparse view CT reconstruction with a group sparse prior

Purpose Numerous techniques based on deep learning have been utilized in sparse view computed tomography (CT) imaging. Nevertheless, the majority of techniques are instinctively constructed utilizing state-of-the-art opaque convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields and neglect nonlocal self-similarity prior information. Obtaining diagnostically valuable images from sparsely sampled projections is a challenging and ill-posed task.Method To address this issue, we propose a unique and understandable model named DCDL-GS for sparse view CT imaging. This model relies on a network comprised of convolutional dictionary learning and a nonlocal group sparse prior. To enhance the quality of image reconstruction, we utilize a neural network in conjunction with a statistical iterative reconstruction framework and perform a set number of iterations. Inspired by group sparsity priors, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Furthermore, our DCDL-GS model incorporates filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight and interpretable convolutional dictionary learning network to enhance the applicability of the model.Results The efficiency of our proposed DCDL-GS model in preserving edges and recovering features is demonstrated by the visual results obtained on the LDCT-P and UIH datasets. Compared to the results of the most advanced techniques, the quantitative results are enhanced, with increases of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse prior.Conclusion In this paper, we create a consolidated and enhanced mathematical model by integrating projection data and prior knowledge of images into a deep iterative model. The model is more practical and interpretable than existing approaches. The results from the experiment show that the proposed model performs well in comparison to the others.

Improved YOLOv7 model for insulator defect detection

<abstract> <p>Insulators are crucial insulation components and structural supports in power grids, playing a vital role in the transmission lines. Due to temperature fluctuations, internal stress, or damage from hail, insulators are prone to injury. Automatic detection of damaged insulators faces challenges such as diverse types, small defect targets, and complex backgrounds and shapes. Most research for detecting insulator defects has focused on a single defect type or a specific material. However, the insulators in the grid's transmission lines have different colors and materials. Various insulator defects coexist, and the existing methods have difficulty meeting the practical application requirements. Current methods suffer from low detection accuracy and mAP0.5 cannot meet application requirements. This paper proposes an improved you only look once version 7 (YOLOv7) model for multi-type insulator defect detection. First, our model replaces the spatial pyramid pooling cross stage partial network (SPPCSPC) module with the receptive filed block (RFB) module to enhance the network's feature extraction capability. Second, a coordinate attention (CA) mechanism is introduced into the head part to enhance the network's feature representation ability and to improve detection accuracy. Third, a wise intersection over union (WIoU) loss function is employed to address the low-quality samples hindering model generalization during training, thereby improving the model's overall performance. The experimental results indicate that the proposed model exhibits enhancements across various performance metrics. Specifically, there is a 1.6% advancement in mAP_0.5, a corresponding 1.6% enhancement in mAP_0.5:0.95, a 1.3% elevation in precision, and a 1% increase in recall. Moreover, the model achieves parameter reduction by 3.2 million, leading to a decrease of 2.5 GFLOPS in computational cost. Notably, there is also an improvement of 2.81 milliseconds in single-image detection speed. This improved model can detect insulator defects for diverse materials, color insulators, and partial damage shapes in complex backgrounds.</p> </abstract>

Multi-Modal Fusion Based on Depth Adaptive Mechanism for 3D Object Detection

Lidars and cameras are critical sensors for 3D object detection in autonomous driving. Despite the increasing popularity of sensor fusion in this field, accurate and robust fusion methods are still under exploration due to non-homogenous representations. In this paper, we find that the complementary roles of point clouds and images vary with depth. An important reason is that the point cloud appearance changes significantly with increasing distance from the Lidar, while the image's edge, color, and texture information are not sensitive to depth. To address this, we propose a fusion module based on the Depth Attention Mechanism (DAM), which mainly consists of two operations: gated feature generation and point cloud division. The former adaptively learns the importance of bimodal features without additional annotations, while the latter divides point clouds to achieve differential fusion of multi-modal features at different depths. This fusion module can enhance the representation ability of original features for different point sets and provide more comprehensive features by using the dual splicing strategy of concatenation and index connection. Additionally, considering point density as a feature and its negative correlation with depth, we build an Adaptive Threshold Generation Network (ATGN) to generate the depth threshold by extracting density information, which can divide point clouds more reasonably. Experiments on the KITTI dataset demonstrate the effectiveness and competitiveness of our proposed models.

A New Siamese Heterogeneous Convolutional Neural Networks Based on Attention Mechanism and Feature Pyramid.

Accuracy and speed are the most important indexes for evaluating many object tracking algorithms. However, when constructing a deep fully convolutional neural network (CNN), the use of deep network feature tracking will cause tracking drift due to the effects of convolution padding, receptive field (RF), and overall network step size. The speed of the tracker will also decrease. This article proposes a fully convolutional siamese network object tracking algorithm that combines the attention mechanism with the feature pyramid network (FPN), and uses heterogeneous convolution kernels to reduce the amount of calculations (FLOPs) and parameters. The tracker first uses a new fully CNN to extract image features, and introduces a channel attention mechanism in the feature extraction process to improve the representation ability of convolutional features. Then use the FPN to fuse the convolutional features of high and low layers, learn the similarity of the fused features, and train the fully CNNs. Finally, the heterogeneous convolutional kernel is used to replace the standard convolution kernel to improve the speed of the algorithm, thereby making up for the efficiency loss caused by the feature pyramid model. In this article, the tracker is experimentally verified and analyzed on the VOT-2017, VOT-2018, OTB-2013, and OTB-2015 datasets. The results show that our tracker has achieved better results than the state-of-the-art trackers.

An Efficient Single Image De-raining Model with Decoupled Deep Networks.

Single image de-raining is an emerging paradigm for many outdoor computer vision applications since rain streaks can significantly degrade the visibility and render the function compromised. The introduction of deep learning (DL) has brought about substantial advancement on de-raining methods. However, most existing DL-based methods use single homogeneous network architecture to generate de-rained images in a general image restoration manner, ignoring the discrepancy between rain location detection and rain intensity estimation. We find that this discrepancy would cause feature interference and representation ability degradation problems which significantly affect de-raining performance. In this paper, we propose a novel heterogeneous de-raining architecture aiming to decouple rain location detection and rain intensity estimation (DLINet). For these two subtasks, we provide dedicated network structures according to their differential properties to meet their respective performance requirements. To coordinate the decoupled subnetworks, we develop a high-order collaborative network learning the dynamic inter-layer interactions between rain location and intensity. To effectively supervise the decoupled subnetworks during training, we propose a novel training strategy that imposes task-oriented supervision using the label learned via joint training. Extensive experiments on synthetic datasets and real-world rainy scenes demonstrate that the proposed method has great advantages over existing state-of-the-art methods.

SFWN: A Novel Semi-Supervised Feature Weighted Neural Network for Gene Data Feature Learning and Mining With Graph Modeling.

Gene expression data can serve for analyzing the genes with changed expressions, the correlation between genes and the influence of different circumstance on gene activities. However, labeling a large number of gene expression data is laborious and time-consuming. The insufficient labeled data pose a challenge to construct the deep learning model. Currently, some graph neural networks (GNN) based on semi-supervised learning mechanism only focus on the feature space and sample space of gene expression data, possibly affecting the accuracy. This article puts forward a novel semi-supervised graph neural network model (SFWN). Firstly, we use the external knowledge of gene expression data for constructing a feature graph, a similarity kernel, and a sample graph for the first time. Later, a novel semi-supervised learning algorithm (SGA) is proposed to extract the data relationship and obtain the global sample structure better. A graph sparse module (SGCN) is also proposed to process sparse representation with gene expression data classification. To overcome the over smoothing problem, a new feature calculation method based on two spaces is proposed to feature representation analysis and calculation in this model. According to a lot of experiments and ablation studies conducted on several public datasets, SFWN exhibits a better effect and is superior to the state-of-the-art approaches (the accuracy and F1-Score are 0.9993 and 0.9899, respectively). Experimental results showed that the proposed SFWN model has strong gene expression feature learning and representation ability, and may provide a new insight and tool for relevant disease diagnosis and clinic practice.

VT-3DCapsNet: Visual tempos 3D-Capsule network for video-based facial expression recognition.

Facial expression recognition(FER) is a hot topic in computer vision, especially as deep learning based methods are gaining traction in this field. However, traditional convolutional neural networks (CNN) ignore the relative position relationship of key facial features (mouth, eyebrows, eyes, etc.) due to changes of facial expressions in real-world environments such as rotation, displacement or partial occlusion. In addition, most of the works in the literature do not take visual tempos into account when recognizing facial expressions that possess higher similarities. To address these issues, we propose a visual tempos 3D-CapsNet framework(VT-3DCapsNet). First, we propose 3D-CapsNet model for emotion recognition, in which we introduced improved 3D-ResNet architecture that integrated with AU-perceived attention module to enhance the ability of feature representation of capsule network, through expressing deeper hierarchical spatiotemporal features and extracting latent information (position, size, orientation) in key facial areas. Furthermore, we propose the temporal pyramid network(TPN)-based expression recognition module(TPN-ERM), which can learn high-level facial motion features from video frames to model differences in visual tempos, further improving the recognition accuracy of 3D-CapsNet. Extensive experiments are conducted on extended Kohn-Kanada (CK+) database and Acted Facial Expression in Wild (AFEW) database. The results demonstrate competitive performance of our approach compared with other state-of-the-art methods.

DER-GCN: Dialog and Event Relation-Aware Graph Convolutional Neural Network for Multimodal Dialog Emotion Recognition.

With the continuous development of deep learning (DL), the task of multimodal dialog emotion recognition (MDER) has recently received extensive research attention, which is also an essential branch of DL. The MDER aims to identify the emotional information contained in different modalities, e.g., text, video, and audio, and in different dialog scenes. However, the existing research has focused on modeling contextual semantic information and dialog relations between speakers while ignoring the impact of event relations on emotion. To tackle the above issues, we propose a novel dialog and event relation-aware graph convolutional neural network (DER-GCN) for multimodal emotion recognition method. It models dialog relations between speakers and captures latent event relations information. Specifically, we construct a weighted multirelationship graph to simultaneously capture the dependencies between speakers and event relations in a dialog. Moreover, we also introduce a self-supervised masked graph autoencoder (SMGAE) to improve the fusion representation ability of features and structures. Next, we design a new multiple information Transformer (MIT) to capture the correlation between different relations, which can provide a better fuse of the multivariate information between relations. Finally, we propose a loss optimization strategy based on contrastive learning to enhance the representation learning ability of minority class features. We conduct extensive experiments on the benchmark datasets, Interactive Emotional Dyadic Motion Capture (IEMOCAP) and Multimodal EmotionLines Dataset (MELD), which verify the effectiveness of the DER-GCN model. The results demonstrate that our model significantly improves both the average accuracy and the F1 value of emotion recognition. Our code is publicly available at https://github.com/yuntaoshou/DER-GCN.

Multiview Deep Learning-based Efficient Medical Data Management for Survival Time Forecasting.

In recent years, data-driven remote medical management has received much attention, especially in application of survival time forecasting. By monitoring the physical characteristics indexes of patients, intelligent algorithms can be deployed to implement efficient healthcare management. However, such pure medical data-driven scenes generally lack multimedia information, which brings challenge to analysis tasks. To deal with this issue, this paper introduces the idea of ensemble deep learning to enhance feature representation ability, thus enhancing knowledge discovery in remote healthcare management. Therefore, a multiview deep learning-based efficient medical data management framework for survival time forecasting is proposed in this paper, which is named as "MDL-MDM" for short. Firstly, basic monitoring data for body indexes of patients is encoded, which serves as the data foundation for forecasting tasks. Then, three different neural network models, convolution neural network, graph attention network, and graph convolution network, are selected to build a hybrid computing framework. Their combination can bring a multiview feature learning framework to realize an efficient medical data management framework. In addition, experiments are conducted on a realistic medical dataset about cancer patients in the US. Results show that the proposal can predict survival time with 1% to 2% reduction in prediction error.

C2BNet: A Deep Learning Architecture with Coupled Composite Backbone for Parasitic EGG Detection in Microscopic Images.

Internet of Medical Things (IoMT) enabled by artificial intelligence (AI) technologies can facilitate automatic diagnosis and management of chronic diseases (e.g., intestinal parasitic infection) based on two-dimensional (2D) microscopic images. To improve the model performance of object detection challenged by microscopic image characteristics (e.g., focus failure, motion blur, and whether zoomed or not), we propose Coupled Composite Backbone Network (C2BNet) to execute the parasitic egg detection task using 2D microscopic images. In particular, the C2BNet backbone adopts a two-path structure-based backbone and leverages model heterogeneity to learn object features from different perspectives. A novel feature composition style is proposed to flow the feature within the coupled composite backbone, and ensure mutual enhancement of feature representation ability among the different paths of the backbone. To further improve the accuracy of the detection results, we propose Multiscale Weighted Box Fusion (WBF) to fuse the location and confidence scores of all bounding boxes predicted from the multiscale feature maps, and iteratively refine the box coordinates to form the final prediction. Experimental results on Chula-ParasiteEgg-11 dataset demonstrate that the C2BNet not only performs satisfactorily compared with state-of-the-art methods, but also can focus more on learning detailed morphology features and abundant semantic features, resulting in more precise detection for parasitic eggs located in the 2D microscopic image.

RPFNet: Recurrent Pyramid Frequency Feature Fusion Network for Instance Segmentation in Side-Scan Sonar Images

Side-scan sonar (SSS) is an essential acoustic sensor device for obtaining underwater information. The instance segmentation of sonar images can effectively locate and detect underwater objects. Although various CNN-based frameworks have achieved promising results in natural image instance segmentation, the noise interference, highlight shadow, and blurred edge in sonar images bring more significant challenges for sonar image instance segmentation. To solve these problems, we propose a novel recurrent pyramid frequency feature fusion network (RPFNet), which mainly consists of the pyramid frequency feature fusion network (PFN), recurrent residual attention mechanism (RRAM), mask prediction module, and semantic segmentation module. By enhancing and fusing different frequency features of SSS images, PFN can effectively extract fine-grained features and reduce background information interference. The RRAM uses residual structure and attention mechanism to enhance the correlation of different frequency features and improve nonlinear feature representation ability. The mask prediction and semantic segmentation modules are used to discriminate object instance categories and generate corresponding semantic segmentation results. We extensively evaluate the proposed framework on the real-scenes sonar image dataset. The evaluation results demonstrate that the proposed method outperforms the state-of-the-art methods in various evaluation metrics. Code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/darkseid-arch/SonarRPFNet</uri> .

Progressive Bidirectional Feature Extraction and Enhancement Network for Quality Evaluation of Night-Time Images

Blind image quality assessment (BIQA) has received increasing attention in the past decades. However, it still remains inadequately researched on BIQA for night-time images suffering from the diverse authentic degradations. Since the intrinsic content degradations of night-time images are highly related to the illumination, how to use the connection between content and illumination to enhance the feature representation ability is the key issue in designing BIQA methods for night-time images. In this paper, we first construct an ultra-high-definition night-time image dataset (UHD-NID) with high image resolution and abundant parameter settings. UHD-NID contains 1600 images with a high resolution of 5616×3744, and each group of images contains ten exposure levels. Then, we conduct subjective assessment and analyze the subjective data to obtain a mean opinion score to each image in UHD-NID. To enhance the feature representation ability in content and illumination, we propose a progressive bidirectional feature extraction and enhancement network (PBFEE-Net). In addition, we use a decomposition network to decompose the input image into the reflectance and illumination, which can facilitate the ability of feature extraction to some extent. The experimental results show that our proposed method achieves superior performance in evaluating the quality of night-time images. The dataset and code will be released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/NBUsjl/UHD-NID</uri> .

Self-adaptive subspace representation from a geometric intuition

In this paper, we address the unsupervised subspace learning task from a geometric intuition, which offers a direct understanding of the data representation. First, we consider all subspaces of the Euclidean space as a series of graded Grassmannian manifolds, and represent them by orbits of rotation group action. Then, we reformulate the unsupervised subspace learning by a least square problem with respect to rotation and projection operator. Second, we introduce a low-rank regularization to obtain a low-dimensional and robust subspace representation. Then, the model is translated into a minimization problem on the Grassmannian manifold. By dividing the model into two subproblems of solving the optimal rotation and subspace dimension, we design an alternating iteration strategy, where the locally geodesic structure of the rotation group and the unconstrained quadratic 0-1 programming are utilized. Finally, we apply the proposed method to the image classification problem on five benchmark datasets and compare it with nine state-of-the-art methods. Numerical results show that our proposed method has better feature representation ability and almost achieves the best performance in terms of classification accuracy and robustness.

Enhancing deep feature representation in self-knowledge distillation via pyramid feature refinement

In recent years, various self-knowledge distillation approaches have been proposed to reduce the cost of training teacher networks. However, these methods often overlook the significance of deep features. To address this limitation and strengthen the capability of deep features while preserving the ability of shallow features, we propose performing Self-Knowledge Distillation via Pyramid Feature Refinement (PR-SKD). Inspired by the representation learning characteristics of deep neural networks, PR-SKD builds a cohort of sub-networks with a pyramid architecture to hierarchically transfer refined information to the target network. According to the different contributions and functions between deep and shallow feature maps, our PR-SKD fully utilizes feature information to improve deep feature representation ability without compromising the capability of shallow feature maps. Extensive experiments on various image classification datasets demonstrate the superiority of our proposed method over widely used state-of-the-art knowledge distillation methods. The code is available at: https://github.com/wo16pao/PR-SKD.

Extracting Citrus-Growing Regions by Multiscale UNet Using Sentinel-2 Satellite Imagery

Citrus is an important commercial crop in many areas. The management and planning of citrus growing can be supported by timely and efficient monitoring of citrus-growing regions. Their complex planting structure and the weather are likely to cause problems for extracting citrus-growing regions from remote sensing images. To accurately extract citrus-growing regions, deep learning is employed, because it has a strong feature representation ability and can obtain rich semantic information. A novel model for extracting citrus-growing regions by UNet that incorporates an image pyramid structure is proposed on the basis of the Sentinel-2 satellite imagery. A pyramid-structured encoder, a decoder, and multiscale skip connections are the three main components of the model. Additionally, atrous spatial pyramid pooling is used to prevent information loss and improve the ability to learn spatial features. The experimental results show that the proposed model has the best performance, with the precision, the intersection over union, the recall, and the F1-score reaching 88.96%, 73.22%, 80.55%, and 84.54%, respectively. The extracted citrus-growing regions have regular boundaries and complete parcels. Furthermore, the proposed model has greater overall accuracy, kappa, producer accuracy, and user accuracy than the object-oriented random forest algorithm that is widely applied in various fields. Overall, the proposed method shows a better generalization ability, higher robustness, greater accuracy, and less fragmented extraction results. This research can support the rapid and accurate mapping of large-scale citrus-growing regions.

Point Cloud Segmentation Network Based on Attention Mechanism and Dual Graph Convolution

To overcome the limitations of inadequate local feature representation and the underutilization of global information in dynamic graph convolutions, we propose a network that combines attention mechanisms with dual graph convolutions. Firstly, we construct a static graph based on the dynamic graph using the K-nearest neighbors algorithm and geometric distances of point clouds. This integration of dynamic and static graphs forms a dual graph structure, compensating for the underutilization of geometric positional relationships in the dynamic graph. Next, edge convolutions are applied to extract edge features from the dual graph structure. To further enhance the capturing ability of local features, we employ attention pooling, which combines max pooling and average pooling operations. Secondly, we introduce channel attention modules and spatial self-attention modules to improve the representation ability of global features and enhance semantic segmentation accuracy in our network. Experimental results on the S3DIS dataset demonstrate that compared to dynamic graph convolution alone, our proposed approach effectively utilizes both semantic and geometric relationships between point clouds using dual graph convolutions while addressing limitations related to insufficient local feature extraction. The introduction of attention mechanisms helps mitigate underutilization issues with global information, resulting in significant improvements in model performance.

Deep Wavelet Convolutional Neural Networks for Multimodal Human Activity Recognition Using Wearable Inertial Sensors.

Recent advances in wearable systems have made inertial sensors, such as accelerometers and gyroscopes, compact, lightweight, multimodal, low-cost, and highly accurate. Wearable inertial sensor-based multimodal human activity recognition (HAR) methods utilize the rich sensing data from embedded multimodal sensors to infer human activities. However, existing HAR approaches either rely on domain knowledge or fail to address the time-frequency dependencies of multimodal sensor signals. In this paper, we propose a novel method called deep wavelet convolutional neural networks (DWCNN) designed to learn features from the time-frequency domain and improve accuracy for multimodal HAR. DWCNN introduces a framework that combines continuous wavelet transforms (CWT) with enhanced deep convolutional neural networks (DCNN) to capture the dependencies of sensing signals in the time-frequency domain, thereby enhancing the feature representation ability for multiple wearable inertial sensor-based HAR tasks. Within the CWT, we further propose an algorithm to estimate the wavelet scale parameter. This helps enhance the performance of CWT when computing the time-frequency representation of the input signals. The output of the CWT then serves as input for the proposed DCNN, which consists of residual blocks for extracting features from different modalities and attention blocks for fusing these features of multimodal signals. We conducted extensive experiments on five benchmark HAR datasets: WISDM, UCI-HAR, Heterogeneous, PAMAP2, and UniMiB SHAR. The experimental results demonstrate the superior performance of the proposed model over existing competitors.

IMSF-Net:An improved multi-scale information fusion network for PPG-based blood pressure estimation

Recently, deep learning (DL) architectures have been widely used for PPG-based blood pressure (BP) monitoring due to their powerful feature extraction ability. However, the DL methods still suffer from limitations. First, the multi-scale time dependency characteristics of PPG require the DL-based methods to have the ability of sufficient feature representation at various scales. Second, the lack of DL model interpretability can lead to concerns about the reliability and generalizability of prediction. In this study, a new PPG-based end-to-end deep learning method, referred to as the IMSF-Net, is proposed for BP estimation, and its advantages are as follows: (1) the improved multi-scale fusion (IMSF) block is designed to extract different-scale feature in a two-channel way, which can obtain the abstract high-level information while avoiding low-level information loss simultaneously; (2) Permutation importance algorithm is firstly adopted to determine what parts of PPG are most useful for automatic BP estimation. On the University of California, Irvine database, the proposed IMSF-Net achieves mean absolute error (MAE) ± standard deviation (STD) of 2.07 ± 2.32 mmHg for systolic blood pressure (SBP) and 1.21 ± 1.51 mmHg for diastolic blood pressure (DBP). On the healthy database, referred to as the VDB, the method achieves MAE ± STD of 1.75 ± 3.98 mmHg for SBP and 1.29 ± 2.3 mmHg for DBP. Both of the performances outperform related previous works. The model interpretation results show that feature grids comprising of Diastolic 1–3, and Systolic 5, which generally cover the waveform from the peak point to the dicrotic notch, have a strong correlation with BP estimation.

SAR-ATR with knowledge hierarchy division and information dissemination networks

Synthetic aperture radar (SAR) images possess diverse domain characteristics that describe targets from multiple perspectives, including scattering center, intensity, phase, azimuth angle, and shadow. The imaging mechanism of SAR images significantly differs from optical images due to its use of radio waves instead of visible light for imaging purposes. However, current deep learning (DL)-based automatic target recognition (ATR) approaches for SAR primarily focus on the intensity information while neglecting the comprehensive consideration of SAR domain characteristics. This limitation results in insufficient expression of target features and hampers further improvement in SAR target recognition performance. To address these issues, this paper proposes a novel SAR target recognition method called KDNets based on information dissemination networks (IDNets) and knowledge hierarchy division (KnHD). KDNets effectively enhances the feature representation ability of SAR targets by exploiting multiple domain characteristics at sample, feature, and decision levels. Specifically, IDNets incorporates scattering center and azimuth angle at sample and feature levels to extract rich multi-scale semantic features for representing SAR targets. At the decision stage, KnHD utilizes azimuth information to rapidly search and fuse prior knowledge about targets from a knowledge base to achieve interpretable and high-precision SAR target recognition. Experimental results on the MSTAR dataset and MA-SAR dataset demonstrate that our proposed KDNets can achieve state-of-the-art performance in SAR target recognition tasks, with the accuracy of 99.75 % in the MSTAR dataset and 98.61 % in the MA-SAR dataset, validating its effectiveness and superiority. Furthermore, this study highlights the significant potential and application prospects of leveraging domain characteristics in SAR-ATR tasks.