Aggregate Characteristics Research Articles

A visible-infrared person re-identification method based on meta-graph isomerization aggregation module

Due to different imaging principles of visible-infrared cameras, there are modal differences between similar person images. For visible-infrared person re-identification (VI-ReID), existing works focus on extracting and aligning cross-modal global descriptors in the shared feature space, while ignoring local variations and graph-structural correlations in cross-modal image pairs. In order to bridge the modal differences with graph-structure between key-parts, a Meta-Graph Isomerization Aggregation Module (MIAM) is proposed, which includes Meta-Graph Node Isomerization Module (MNI) and Dual Aggregation Module (DA). In order to completely describe discriminative in-graph local features, MNI establishes meta-secondary cyclic isomorphism relations of in-graph local features by using a multi-branch embedding generation mechanism. Then, the local features not only contain the limited information of the fixed regions, but also benefit from the neighboring regions. Meanwhile, the secondary node generation process considers similar and different nodes of pedestrian graph structure to reduce the interference of identity differences. In addition, the Dual Aggregation (DA) module combines spatial self-attention and channel self-attention to establish the interdependence of modal heterogeneous graph structure pairs and achieve inter-modal feature aggregation. To match heterogeneous graph structures, a Node Center Joint Mining Loss (NCJM Loss) is proposed to constrain the distance between the node centers of heterogeneous graphs. The experiments performed on the SYSU-MM01, RegDB and LLCM public datasets demonstrate that the proposed method performs excellently in VI-ReID.

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.

Hybrid CNN-transformer network for efficient CSI feedback

In recent years, many deep learning-based methods have been utilized for the feedback of Channel State Information (CSI) in massive MIMO systems. The Transformer-based networks leverage global self-attention mechanisms that can effectively capture remote correlations between antennas, while Convolutional Neural Networks (CNNs) excel in acquiring local information. To balance the advantages of both, this paper proposes an Efficient Feature Aggregation Network called EFANet, which hybrid CNNs and Transformer. Specifically, we propose a Refined Window Multi-head Self-Attention (RW-MSA) through hybrid Convolutional Embedding Unit (CEU) and Window Multi-head Self-Attention (W-MSA) to reduce information loss between windows and achieve efficient feature aggregation. Additionally, we develop a Local Enhanced Feedforward Network (LEFN) to further integrate local information in the CSI matrix and model detailed features of different regions. Finally, the Compensation Unit (CU) is designed to further compensate for global-local features in the CSI matrix. Through the above design, the global and local features are fully interactive to reduce information loss. Numerous experiments have shown that the proposed method achieves better CSI reconstruction performance while reducing computational complexity.

A veracity dissemination consistency-based few-shot fake news detection framework by synergizing adversarial and contrastive self-supervised learning

With the rapid growth of social media, fake news (rumors) are rampant online, seriously endangering the health of mainstream social consciousness. Fake news detection (FEND), as a machine learning solution for automatically identifying fake news on Internet, is increasingly gaining the attentions of academic community and researchers. Recently, the mainstream FEND approaches relying on deep learning primarily involves fully supervised fine-tuning paradigms based on pre-trained language models (PLMs), relying on large annotated datasets. In many real scenarios, obtaining high-quality annotated corpora are time-consuming, expertise-required, labor-intensive, and expensive, which presents challenges in obtaining a competitive automatic rumor detection system. Therefore, developing and enhancing FEND towards data-scarce scenarios is becoming increasingly essential. In this work, inspired by the superiority of semi-/self- supervised learning, we propose a novel few-shot rumor detection framework based on semi-supervised adversarial learning and self-supervised contrastive learning, named Detection Yet See Few (DetectYSF). DetectYSF synergizes contrastive self-supervised learning and adversarial semi-supervised learning to achieve accurate and efficient FEND capabilities with limited supervised data. DetectYSF uses Transformer-based PLMs (e.g., BERT, RoBERTa) as its backbone and employs a Masked LM-based pseudo prompt learning paradigm for model tuning (prompt-tuning). Specifically, during DetectYSF training, the enhancement measures for DetectYSF are as follows: (1) We design a simple but efficient self-supervised contrastive learning strategy to optimize sentence-level semantic embedding representations obtained from PLMs; (2) We construct a Generation Adversarial Network (GAN), utilizing random noises and negative fake news samples as inputs, and employing Multi-Layer Perceptrons (MLPs) and an extra independent PLM encoder to generate abundant adversarial embeddings. Then, incorporated with the adversarial embeddings, we utilize semi-supervised adversarial learning to further optimize the output embeddings of DetectYSF during its prompt-tuning procedure. From the news veracity dissemination perspective, we found that the authenticity of the news shared by these collectives tends to remain consistent, either mostly genuine or predominantly fake, a theory we refer to as “news veracity dissemination consistency”. By employing an adjacent sub-graph feature aggregation algorithm, we infuse the authenticity characteristics from neighboring news nodes of the constructed veracity dissemination network during DetectYSF inference. It integrates the external supervisory signals from “news veracity dissemination consistency” to further refine the news authenticity detection results of PLM prompt-tuning, thereby enhancing the accuracy of fake news detection. Furthermore, extensive baseline comparisons and ablated experiments on three widely-used benchmarks demonstrate the effectiveness and superiority of DetectYSF for few-shot fake new detection under low-resource scenarios.

A cross-modal feature aggregation and enhancement network for hyperspectral and LiDAR joint classification

Advancements in Earth observation technologies have greatly enhanced the potential of integrating hyperspectral (HS) images with Light Detection and Ranging (LiDAR) data for land use and land cover classification. Despite this, most existing methods primarily focus on employing deep network layers to extract features from two heterogeneous data modalities, often overlooking a gradual modeling data representation approach from shallow to deep layers. Furthermore, excessive network layers can result in the deterioration of modality-specific features, therefore lowering the classification performance. The paper proposed a novel cross-modal feature aggregation and enhancement network for the joint classification of HSI and LiDAR data. Initially, a cross-modal feature fusion module is developed to exploit spatial scale consistency to complete the interchange and fusion of feature embedding at the pixel level, preserving the original information from the two heterogeneous modalities to a certain degree. Then two straightforward strategies (i.e., addition and concatenation) are employed in the shallow network layers before being sent to the transformer encoder. The former facilitates the model’s ability to discern more subtle distinctions and refine spatial location details. The latter ensures the preservation of information integrity, effectively mitigating the risk of feature loss. Moreover, invertible neural networks and a feature enhancement module are introduced, leveraging the complementary information of HSI and LiDAR data to enhance the detail and texture information extracted in deeper layers. Extensive experiments on Houston2013, Trento, and MUUFL datasets demonstrate that the proposed method outperforms several state-of-the-art models in three evaluation metrics, achieving an accuracy improvement of up to 2%. The proposed model brings new inspirations for HSI and LiDAR classification, which is critical for accurate environmental monitoring, urban planning, and precision agriculture. The source code is publicly accessible at https://github.com/zhangyiyan001/CMFAEN.

A hierarchical and interlamination graph self-attention mechanism-based knowledge graph reasoning architecture

Knowledge Graph (KG) is an essential research field in graph theory, but its inherent incompleteness and sparsity influence its performance in several fields. Knowledge Graph Reasoning (KGR) aims to ameliorate those problems by mining new knowledge from subsistent knowledge. As one of the downstream tasks of KGR, link prediction is of great significance for improving the quality of KG. Recently, the Graph Neural Network (GNN)-based method became the most effective way to achieve the link prediction task. However, it still suffers from problems such as incomplete neighbor and relation-level information aggregation and unstable learning of the entity's features. To improve those issues, a Hierarchical and Interlamination Graph Self-attention Mechanism-based (HIGSM) plug-and-play architecture is proposed for KGR in this paper. It is composed of three-level layers: feature extractor, encoder, and decoder. The feature extractor makes our architecture more effective and stable for the retrieval of new features. The encoder is equipped with a two-stage encoding mechanism accompanied by two mixture-of-expert strategies, which enables our architecture to capture more practical reasoning information to improve prediction accuracy and generalization of the model. The decoder can use existing KGR models and compute the scores of triples in KG. The extensive experimental results and ablation studies on four KGs unambiguously demonstrate the state-of-the-art prediction performance of the proposed HIGSM architecture compared to current GNN-based methods.

Experimental research on the horizontally getting together behaviors of acoustically manipulated bi-particle

This study aims at the controllability of acoustically manipulated non-contact aggregation of bi-particle. Based on the acoustic wave radiation model of the transducer and the acoustic wave interference theory, the mathematical model between the spatial levitation point and the phase of the phased array ultrasonic array unit is established. A double-sided phased array test system was developed and the phase calculation algorithm for independently manipulating bi-particle was optimized. The algorithm is capable of independently distributing the energy applied to each levitation point. Through simulation and experiment, the horizontally aggregation characteristics of two levitated particles are investigated, and a interesting relationship between particles aggregation and standing wave phase difference is revealed, which follows the law of “attraction in the same phase but repulsion in the opposite phase”. By adjusting the tilt angle of the standing wave acoustic trap, the critical distance when particles to accelerate and collision is sharply reduced from 1.5λ to 0.5λ, which provides a new perspective and potential application path for acoustic manipulation technology.

Lateral Piezoelectricity of Alzheimer's Aβ Aggregates.

Alzheimer's disease (AD) is the most frequent neurodegenerative disorder in the elderly aged over 65. The extracellular accumulation of beta-amyloid (Aβ) aggregates in the brain is considered as the major event worsening the AD symptoms, but its underlying reason has remained unclear. Here the piezoelectric characteristics of Aβ aggregates are revealed. The vector piezoresponse force microscopy (PFM) analysis results exhibit that Aβ fibrils have spiraling piezoelectric domains along the length and a lateral piezoelectric constant of 44.1 pC N-1. Also, the continuous sideband Kelvin probe force microscopy (KPFM) images display that the increment of charge-induced surface potential on a single Aβ fibril is allowed to reach above +1700mV in response to applied forces. These findings shed light on the peculiar mechano-electrical surface properties of pathological Aβ fibrils that exceed those of normal body components.

Electromigration Analysis for Interconnects Using Improved Graph Convolutional Network with Edge Feature Aggregation.

Electromigration (EM) is a critical reliability issue in integrated circuits and is becoming increasingly significant as fabrication technology nodes continue to advance. The analysis of the hydrostatic stress, which is paramount in electromigration studies, typically involves solving complex physical equations (partial differential equations, or PDEs in this case), which is time consuming, inefficient and not practical for full-chip EM analysis. In this paper, a novel approach is proposed, conceptualizing circuit interconnect trees as a graph within a graph neural network framework. Using finite element solution software, ground truth hydrostatic stress values were obtained to construct a dataset of interconnected trees with hydrostatic stress values for each node. An improved Graph Convolutional Network (GCN) augmented with edge feature aggregation and attention mechanism was then trained employing the dataset, yielding a model capable of predicting hydrostatic stress values for nodes in an interconnect tree. The results show that our model demonstrated a 15% improvement in the Root Mean Square Error (RMSE) compared to the original GCN model and improved the solution speed greatly compared to traditional finite element software.

Deep learning-based fault diagnosis of servo motor bearing using the attention-guided feature aggregation network

This paper introduces a novel approach to fault detection in the servo motor bearings of industrial robots within the context of Industry 4.0 prognostics and health management. The proposed solution leverages the innovative feature aggregation network for robotic fault detection in the application of smart factory. Overcoming challenges associated with traditional techniques that include handcrafted features, transfer learning, and deep learning models, the proposed approach offers a hierarchical information aggregation mechanism. The model is customized through hyperparameter tuning, resulting in a streamlined architecture with significantly fewer parameters. This parameter efficiency is notably distinct when compared to off-the-shelf transfer learning models that commonly feature extensive parameter counts in the range of hundreds of thousands or millions. The proposed model subjected to rigorous validation across diverse experimental scenarios that affirm its adaptability and robust performance. The model showcases accuracy in fault detection under both simple and welding motion scenarios, while its generalization capabilities are demonstrated as it successfully predicts health states in welding motion, showcasing versatility and reliability across various operational scenarios.

Segmentation Network for Multi-Shape Tea Bud Leaves Based on Attention and Path Feature Aggregation

Accurately detecting tea bud leaves is crucial for the automation of tea picking robots. However, challenges arise due to tea stem occlusion and overlapping of buds and leaves, presenting varied shapes of one bud–one leaf targets in the field of view, making precise segmentation of tea bud leaves challenging. To improve the segmentation accuracy of one bud–one leaf targets with different shapes and fine granularity, this study proposes a novel semantic segmentation model for tea bud leaves. The method designs a hierarchical Transformer block based on a self-attention mechanism in the encoding network, which is beneficial for capturing long-range dependencies between features and enhancing the representation of common features. Then, a multi-path feature aggregation module is designed to effectively merge the feature outputs of encoder blocks with decoder outputs, thereby alleviating the loss of fine-grained features caused by downsampling. Furthermore, a refined polarized attention mechanism is employed after the aggregation module to perform polarized filtering on features in channel and spatial dimensions, enhancing the output of fine-grained features. The experimental results demonstrate that the proposed Unet-Enhanced model achieves segmentation performance well on one bud–one leaf targets with different shapes, with a mean intersection over union (mIoU) of 91.18% and a mean pixel accuracy (mPA) of 95.10%. The semantic segmentation network can accurately segment tea bud leaves, providing a decision-making basis for the spatial positioning of tea picking robots.

Reverse cross-refinement network for camouflaged object detection

Due to the high intrinsic similarity between camouflaged objects and the background, camouflaged objects often exhibit blurred boundaries, making it challenging to distinguish the boundaries of objects. Existing methods still focus on the overall regional accuracy but not on the boundary quality and are not competent to identify camouflaged objects from the background in complex scenarios. Thus, we propose a novel reverse cross-refinement network called RCR-Net. Specifically, we design a diverse feature enhancement module that simulates the correspondingly expanded receptive fields of the human visual system by using convolutional kernels with different dilation rates in parallel. Also, the boundary attention module is used to reduce the noise of the bottom features. Moreover, a multi-scale feature aggregation module is proposed to transmit the diverse features from pixel-level camouflaged edges to the entire camouflaged object region in a coarse-to-fine manner, which consists of reverse guidance, group guidance, and position guidance. Reverse guidance mines complementary regions and details by erasing already estimated object regions. Group guidance and position guidance integrate different features through simple and effective splitting and connecting operations. Extensive experiments show that RCR-Net outperforms the existing 18 state-of-the-art methods on four widely-used COD datasets. Especially, compared with the existing top-1 model HitNet, RCR-Net significantly improves the performance by ∼16.4% (Mean Absolute Error) on the CAMO dataset, showing that RCR-Net could accurately detect camouflaged objects.

HQ-Net: A heatmap-based query backbone for point cloud understanding

With the advancement of sensor technology, including LiDAR and RGB-D cameras, tasks related to point cloud understanding have gained widespread application. The sampling and learning of feature points play a crucial role in point cloud understanding, representing a fundamental and essential aspect of 3D computer vision. In the realm of point cloud processing, traditional methods such as Farthest Point Sampling (FPS) are frequently employed to select feature points. These points are then used in conjunction with effective feature aggregation operators to facilitate reasoning. However, these traditional sampling methods primarily focus on the Euclidean distance between points, lacking a comprehensive consideration of point cloud features. To address this limitation, we introduce HQ-Net, a novel point cloud understanding model designed to optimize feature point sampling using a Heatmap-based Query Backbone. The Heatmap-based Query Backbone utilizes the Heatmap Module to select category-specific point features, effectively generating a heatmap tailored to the category features and automatically extracting features from the heatmap. Subsequently, the proposed Query Encoder is employed to facilitate the interaction between point features and query features, providing mutual guidance and enhancing the model’s ability to capture spatial structure and semantic information within point clouds. Additionally, we propose task-specific heads, such as classification and segmentation heads for different tasks, which can be seamlessly integrated with the backbone to achieve excellent performance. In various point cloud understanding tasks, including shape classification, part segmentation, and semantic segmentation, HQ-Net demonstrates excellent performance.

Benchmarking computational methods for single-cell chromatin data analysis

BackgroundSingle-cell chromatin accessibility assays, such as scATAC-seq, are increasingly employed in individual and joint multi-omic profiling of single cells. As the accumulation of scATAC-seq and multi-omics datasets continue, challenges in analyzing such sparse, noisy, and high-dimensional data become pressing. Specifically, one challenge relates to optimizing the processing of chromatin-level measurements and efficiently extracting information to discern cellular heterogeneity. This is of critical importance, since the identification of cell types is a fundamental step in current single-cell data analysis practices.ResultsWe benchmark 8 feature engineering pipelines derived from 5 recent methods to assess their ability to discover and discriminate cell types. By using 10 metrics calculated at the cell embedding, shared nearest neighbor graph, or partition levels, we evaluate the performance of each method at different data processing stages. This comprehensive approach allows us to thoroughly understand the strengths and weaknesses of each method and the influence of parameter selection.ConclusionsOur analysis provides guidelines for choosing analysis methods for different datasets. Overall, feature aggregation, SnapATAC, and SnapATAC2 outperform latent semantic indexing-based methods. For datasets with complex cell-type structures, SnapATAC and SnapATAC2 are preferred. With large datasets, SnapATAC2 and ArchR are most scalable.

Global Context Relation-Guided Feature Aggregation Network for Salient Object Detection in Optical Remote Sensing Images

With the rapid development of deep neural networks, salient object detection has achieved great success in natural images. However, detecting salient objects from optical remote sensing images still remains a challenging task due to the diversity of object types, scale, shape and orientation variations, as well as cluttered backgrounds. Therefore, it is impractical to directly leverage methods designed for natural images to detect salient objects in optical remote sensing images. In this work, we present an end-to-end deep neural network for salient object detection in optical remote sensing images via global context relation-guided feature aggregation. Since the objects in remote sensing images often have a scattered distribution, we design a global context relation module to capture the global relationships between different spatial positions. In order to effectively integrate low-level appearance features as well as high-level semantic features for enhancing the final performance, we develop a feature aggregation module with the global context relation information as guidance and embed it into the backbone network to refine the deep features in a progressive manner. Instead of using traditional binary cross entropy as a training loss which treats all pixels equally, we design a weighted binary cross entropy to capture local surrounding information of different pixels. Extensive experiments on three public datasets are conducted to validate the efficiency of the proposed network and the results demonstrate that our proposed method consistently outperforms other competitors.

EDASNet: efficient dynamic adaptive-scale network for infrared pedestrian detection

Abstract Infrared images are widely utilized due to their exceptional anti-interference capabilities. However, challenges such as low resolution and an absence of detailed texture can impede the effective recognition of multi-scale target information, particularly for small targets. To address these issues, we introduce a multi-scale detection framework named efficient dynamic adaptive-scale network (EDASNet), which focuses on enhancing the feature extraction of small objects while ensuring efficient detection of multi-scale. Firstly, we design a lightweight dynamic enhance network as the backbone for feature extraction. It mainly includes a lightweight adaptive-weight downsampling module and a dynamic enhancement convolution module. In addition, a multi-scale aggregation feature pyramid network is proposed, which improves the perception effect of small objects through a multi-scale convolution module. Then, the Repulsion Loss term was introduced based on CIOU to effectively solve the missed detection problem caused by target overlap. Finally, the dynamic head was used as the network detection head, and through the superposition of dynamic convolution and multiple attention, the network was able to accurately realize multi-scale object detection. Comprehensive experiments show that EDASNet outperforms existing efficient models and achieves a good trade-off between speed and accuracy.

SW-YOLOX: A YOLOX-based real-time pedestrian detector with shift window-mixed attention mechanism

Pedestrian detection is a critical research area in computer vision with practical applications. This paper addresses this key topic by providing a novel lightweight model named Shift Window-YOLOX (SW-YOLOX). The purpose of SW-YOLOX is to significantly enhance the robustness and real-time performance of pedestrian detection under practical application requirements. The proposed method incorporates a novel Shift Window-Mixed Attention Mechanism (SW-MAM), which combines spatial and channel attention for effective feature extraction. In addition, we introduce a novel up-sampling layer, PatchExpandingv2, to enhance spatial feature representation while maintaining computational efficiency. Furthermore, we propose a novel Shift Window-Path Aggregation Feature Pyramid Network (SW-PAFPN) to integrate with the YOLOX detector, further enhancing feature extraction and the robustness of pedestrian detection. Experimental results validated on challenging datasets such as CrowdHuman, MOT17Det, and MOT20Det demonstrate the competitive performance of the proposed SW-YOLOX compared to state-of-the-art methods and its pedestrian detection performance in crowded and complex scenes.

RAAFNet: Reverse Attention Adaptive Fusion Network for Large-Scale Point Cloud Semantic Segmentation

Point cloud semantic segmentation is essential for comprehending and analyzing scenes. However, performing semantic segmentation on large-scale point clouds presents challenges, including demanding high memory requirements, a lack of structured data, and the absence of topological information. This paper presents a novel method based on the Reverse Attention Adaptive Fusion network (RAAFNet) for segmenting large-scale point clouds. RAAFNet consists of a reverse attention encoder–decoder module, an adaptive fusion module, and a local feature aggregation module. The reverse attention encoder–decoder module is applied to extract point cloud features at different scales. The adaptive fusion module enhances fine-grained representation within multi-resolution feature maps. Furthermore, a local aggregation classifier is introduced, which aggregates the features of neighboring points to the center point in order to leverage contextual information and enhance the classifier’s perceptual capability. Finally, the predicted labels are generated. Notably, our method excels at extracting point cloud features across different dimensions and produces highly accurate segmentation results. Experimental results on the Semantic3D dataset achieved an overall accuracy of 89.9% and a mIoU of 74.4%.

Effect of Aggregate Characteristics and Distribution on the Mechanical Characteristics of Recycled Concrete

Effect of Aggregate Characteristics and Distribution on the Mechanical Characteristics of Recycled Concrete

MS23D: A 3D object detection method using multi-scale semantic feature points to construct 3D feature layer

LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and hollowness of point clouds create some difficulties for voxel-based methods. The sparsity of point clouds makes it challenging to describe the geometric features of objects. The hollowness of point clouds poses difficulties for the aggregation of 3D features. We propose a two-stage 3D object detection framework, called MS23D. (1) We propose a method using voxel feature points from multi-branch to construct the 3D feature layer. Using voxel feature points from different branches, we construct a relatively compact 3D feature layer with rich semantic features. Additionally, we propose a distance-weighted sampling method, reducing the loss of foreground points caused by downsampling and allowing the 3D feature layer to retain more foreground points. (2) In response to the hollowness of point clouds, we predict the offsets between deep-level feature points and the object’s centroid, making them as close as possible to the object’s centroid. This enables the aggregation of these feature points with abundant semantic features. For feature points from shallow-level, we retain them on the object’s surface to describe the geometric features of the object. To validate our approach, we evaluated its effectiveness on both the KITTI and ONCE datasets.