检索结果-内蒙古大学图书馆

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

CAAI Transactions on intelligence Technology 2023年第4期8卷 1178-1190页

作者： Hailong Ning Tao Lei Mengyuan An Hao Sun Zhanxuan Hu Asoke K.Nandi School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsShaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'anChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anChina School of Electronic Information and Artificial Intelligence Shaanxi University of Science and TechnologyXi'anChina School of Computer Central China Normal UniversityWuhanChina Department of Electronic and Electrical Engineering Brunel University LondonLondonUK Xi'an Jiaotong University Xi'anChina

Aerial scene recognition(ASR)has attracted great attention due to its increasingly essential *** of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ***,the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features,leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene *** addition,existing methods may suffer from poor generalisations due to millions of to‐belearnt parameters and inconsistent predictions between global and local *** tackle these problems,this study proposes a scale‐wise interaction fusion and knowledge distillation(SIF‐KD)network for learning robust and discriminative features with scaleinvariance and background‐independent *** main highlights of this study include two *** the one hand,a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene ***,a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local *** the other hand,a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during *** experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%,98.74%and 95.47%on the UCM,AID and NWPU‐RESISC45 datasets,respectively,compared with state of the arts.

关键词： deep learning image analysis image classification information fusion

来源：评论

学校读者我要写书评

暂无评论

Trust-Region Based Stochastic Variational Inference for Distributed and Asynchronous Networks

引用

Journal of Systems science & Complexity 2022年第6期35卷 2062-2076页

作者： FU Weiming QIN Jiahu LING Qing KANG Yu YE Baijia Department of Automation University of Science and Technology of ChinaHefei 230027China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China School of Computer Science and Engineering and Guangdong Province Key Laboratory of Computational ScienceSun Yat-Sen UniversityGuangzhou 510006China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230027China

Stochastic variational inference is an efficient Bayesian inference technology for massive datasets,which approximates posteriors by using noisy gradient *** stochastic variational inference can only be performed in a centralized manner,which limits its applications in a wide range of situations where data is possessed by multiple ***,this paper develops a novel trust-region based stochastic variational inference algorithm for a general class of conjugate-exponential models over distributed and asynchronous networks,where the global parameters are diffused over the network by using the Metropolis rule and the local parameters are updated by using the trust-region ***,a simple rule is introduced to balance the transmission frequencies between neighboring nodes such that the proposed distributed algorithm can be performed in an asynchronous *** utility of the proposed algorithm is tested by fitting the Bernoulli model and the Gaussian model to different datasets on a synthetic network,and experimental results demonstrate its effectiveness and advantages over existing works.

关键词： Asynchronous networks Bayesian inference distributed algorithm stochastic variational inference trust-region method

来源：评论

学校读者我要写书评

暂无评论

MSCVP: Multiscale Network Emulation Based on the Integration of Modeling, Simulation, Container, Virtualization, and Physical Networks 3rd

MSCVP: Multiscale Network Emulation Based on the Integration...

引用

3rd International Conference on Cyberspace Simulation and Evaluation, CSE 2024

作者： Wang, Xiaofeng Zhang, Guoxiu Jia, Yan He, Xinyi Hu, Ning School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Pengcheng Laboratory Shenzhen China Shenzhen China

ISBN: (纸本)9789819645022

A cyber range, a special type of computer network emulation environment, allows users to evaluate network security technologies. Traditional network emulation methods, such as packet-level discrete event simulation, have difficulty meeting the realistic network security evaluation requirements of a cyber range. Thus, a series of new technologies, such as container-based network emulation and virtualization-based network emulation, have emerged. The key problem in network emulation is the contradiction between fidelity and cost. To solve this problem, considering the respective advantages of mathematical modeling, packet-level discrete event simulation, container, virtualization and physical networks, this paper introduces a multiscale network emulation method based on the above five methods, named MSCVP, to achieve a tradeoff between fidelity and cost. To improve the emulation performance, on the basis of cloud computing platforms, MSCVP focuses on the seamless integration of packet-level discrete event simulation, container, virtualization and physical networks. Given the dynamics of network topologies, MSCVP further integrates mathematical modeling. The experiments show that MSCVP can achieve seamless integration of the above five methods, enabling worm propagation at the million-node level and dynamic network emulation of space–ground integrated information networks. Compared with the other methods, MSCVP enhances the efficiency of network emulation deployment, achieving an implemented of 56.87%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

FedDGL: Federated Dynamic Graph Learning for Temporal Evolution and Data Heterogeneity 16

FedDGL: Federated Dynamic Graph Learning for Temporal Evolut...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Xie, Zaipeng Li, Likun Chen, Xiangbin Yu, Hao Huang, Qian Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China College of Artificial Intelligence and Automation Hohai University Nanjing China

Federated graph learning enhances federated learning by enabling privacy-preserving collaborative training on distributed graph data. While traditional methods are effective in managing data heterogeneity, they typically assume static graph structures, overlooking the dynamic nature of real-world graphs. Integrating federated graph learning with dynamic graph neural networks addresses this issue but often fails to retain previously acquired knowledge, limiting generalization for both global and personalized models. This paper proposes FedDGL, a novel framework designed to address temporal evolution, and data heterogeneity in federated dynamic graph learning. Unlike conventional approaches, FedDGL captures temporal dynamics through a global knowledge distillation technique and manages client heterogeneity using a global prototype-based regularization method. The framework employs contrastive learning to generate global prototypes, enhancing feature representation while utilizing a prototype similarity-based personalized aggregation strategy for effective adaptation to local and global data distributions. Experiments on multiple benchmark datasets show that FedDGL achieves significant performance improvements over state-of-the-art methods, with up to 9.02% and 8.77% gains in local and global testing, respectively, compared to FedAvg. These results highlight FedDGL’s effectiveness in improving personalized and global model performance in dynamic, heterogeneous federated graph learning scenarios. © 2024 Z. Xie, L. Li, X. Chen, H. Yu & Q. Huang.

关键词： Dynamic Graph Learning Federated Graph Learning Knowledge Distillation Personalized Aggregation Prototype Learning Temporal Evolution

来源：评论

学校读者我要写书评

暂无评论

The Immense Impact of Reverse Edges on Large Hierarchical Networks

引用

Engineering 2024年第5期36卷 240-249页

作者： Haosen Cao Bin-Bin Hu Xiaoyu Mo Duxin Chen Jianxi Gao Ye Yuan Guanrong Chen Tamás Vicsek Xiaohong Guan Hai-Tao Zhang MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems State Key Laboratory of Intelligent Manufacturing Equipment and TechnologySchool of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingapore 639798Singapore Jiangsu Key Laboratory of Networked Collective Intelligence School of MathematicsSoutheast UniversityNanjing 210096China Department of Computer Science Rensselaer Polytechnic InstituteTroyNY 12180USA Department of Electronic Engineering City University of Hong KongHong Kong 999077China Department of Biological Physics Eötvös UniversityBudapest 1117Hungary MOE Key Laboratory for Intelligent Networks and Network Security School of Automation Science and EngineeringXi’an Jiaotong UniversityXi’an 710049China

Hierarchical networks are frequently encountered in animal groups,gene networks,and artificial engineering systems such as multiple robots,unmanned vehicle systems,smart grids,wind farm networks,and so *** structure of a large directed hierarchical network is often strongly influenced by reverse edges from lower-to higher-level nodes,such as lagging birds’howl in a flock or the opinions of lowerlevel individuals feeding back to higher-level ones in a social *** study reveals that,for most large-scale real hierarchical networks,the majority of the reverse edges do not affect the synchronization process of the entire network;the synchronization process is influenced only by a small part of these reverse edges along specific *** surprisingly,a single effective reverse edge can slow down the synchronization of a huge hierarchical network by over 60%.The effect of such edges depends not on the network size but only on the average in-degree of the involved *** overwhelming majority of active reverse edges turn out to have some kind of“bunching”effect on the information flows of hierarchical networks,which slows down synchronization *** finding refines the current understanding of the role of reverse edges in many natural,social,and engineering hierarchical networks,which might be beneficial for precisely tuning the synchronization rhythms of these *** study also proposes an effective way to attack a hierarchical network by adding a malicious reverse edge to it and provides some guidance for protecting a network by screening out the specific small proportion of vulnerable nodes.

关键词： Synchronizability Large hierarchical networks Reverse edges Information flows Complex networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Switching Mechanism of Satellite and Terrestrial Links for Satellite Internet and Simulation Evaluation 3rd

An Efficient Switching Mechanism of Satellite and Terrestr...

引用

3rd International Conference on Cyberspace Simulation and Evaluation, CSE 2024

作者： He, Xinyi Wang, Xiaofeng Zhang, Yi Hu, Ning School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Pengcheng Laboratory Shenzhen518000 China

ISBN: (纸本)9789819645022

In network simulation, switching mechanism technology provides strong support for resource allocation and transmission efficiency in satellite internet. However, the switching mechanism of existing network simulation technology cannot simultaneously meet the requirements for communication quality and communication time in scenarios of frequent switching. In view of the limitations of excessive switching times and insufficient access duration posed by the general switching strategy, this study ingeniously combines the advantage of the single-satellite holding strategy in terms of access duration with the general elevation angle limit strategy. Subsequently, a brand-new multi-criteria satellite and terrestrial link switching mechanism is proposed, thereby achieving a dual guarantee of communication quality and communication time. Based on the proposed multi-criteria satellite and terrestrial link switching mechanism, a new link performance simulation technology has been developed. This technology can not only simulate the real-time parameters of the link but also simulate the switching state of the satellite and terrestrial link. Experiments show that compared with the elevation angle limit strategy, the proposed multi-criteria switching strategy reduces the number of satellite and ground link switches by 46.5% and increases the single communication duration by 92.9%. At the same time, it can realize real-time dynamic performance simulation and switching simulation of the link, optimize the problem of insufficient dynamics of link simulation, and further improve the fidelity of the simulation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Satellite simulators

来源：评论

学校读者我要写书评

暂无评论

SS-WSSS: Small-Scale Weakly Supervised Semantic Segmentation for Histopathology Image

SS-WSSS: Small-Scale Weakly Supervised Semantic Segmentation...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Jiatai Han, Guoqiang Zhou, Jingxuan Shi, Zhenwei Liu, Zaiyi Han, Chu South China University of Technology Guangzhou China Shenzhen China South China University of Technology School of Computer Science and Engineering Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China

ISBN: (纸本)9798350386226

Semantic segmentation for histopathology images is one of the fundamental tasks in computational pathology. Due to the high cost of pixel-level annotation acquisition, the weakly supervised semantic segmentation (WSSS) attempts to achieve information-intensive segmentation task for histopathology images to reduce the labeling effort of pathologists by leveraging image-level labels. However, traditional WSSS requires a large-scale training set with image-level labels, which still imposes considerable labeling costs on pathologists. To this end, this work proposes a Small-Scale Weakly Supervised Semantic Segmentation (SS-WSSS) approach to achieve the comparable performance only with small-scale weakly-labeled data to further reduce pathologist's labeling effort. Since histopathology images can easily generate massive unlabeled data, our SS-WSSS aims to learn with the unlabeled data to bridge the information gap. First, we propose a Single-to-Multi Prototype Similarity (S2M-PS) method to generate reliable pseudo-labels for unlabeled data by measuring the similarity between single-label prototypes and multi-label feature maps. Then, we introduce a Cross-Task CoTraining (CT2) method for pseudo-supervision of models with pseudo-labels self-refinement to avoid overfitting to noisy labels. We conduct the experiment on two public datasets to demonstrate the effectiveness of our SS-WSSS. In the experiment, our method achieves comparable performance with SOTA methods only using 30% labeled data. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

来源：评论

学校读者我要写书评

暂无评论

CSDNet: Contrastive Similarity Distillation Network for Multi-lingual Image-Text Retrieval 12th

CSDNet: Contrastive Similarity Distillation Network for Mul...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Lu, Shichen Guo, Longteng He, Xingjian Zhu, Xinxin Liu, Jing Liu, Si School of Computer Science and Engineering Beihang University Beijing100191 China The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China Institute of Artificial Intelligence Beihang University Beijing100191 China

ISBN: (纸本)9783031463105

Cross-modal image-text retrieval is a crucial task in the field of vision and language, aimed at retrieving the relevant samples from one modality as per the given user expressed in another modality. While most methods developed for this task have focused on English, recent advances expanded the scope of this task to the Multi-lingual domain. However, these methods face challenges due to the limited availability of annotated data in non-English languages. In this work, we propose a novel method that leverages an English pre-training model as a teacher to improve Multi-lingual image-text retrieval performance. Our method trains a student model that produces better Multi-lingual image-text similarity scores by learning from the English image-text similarity scores of the trained teacher. We introduce the contrastive loss to align the two different representations of the image and text, and the Contrastive Similarity Distillation loss to align the Multi-lingual image-text distribution of the student with that of the English teacher. We evaluate our method on two popular datasets, i.e., MS-COCO and Flickr-30K, and achieve state-of-the-art performance. Our approach shows significant improvement over existing methods and has potential for practical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Semantic Mapping for Robotics: Survey, Trends and Challenges

SSRN

引用

SSRN 2025年

作者： Georgevich Ferreira, Bruno Miranda de Sousa, Armando Jorge Reis, Luis Paulo Edge Innovation Center Federal University of Alagoas Alagoas Brazil FEUP - Faculty of Engineering of the University of Porto Porto Portugal LIACC - LASI LA - Artificial Intelligence and Computer Science Laboratory Porto Portugal INESC TEC - INESC Technology and Science Porto Portugal

Robots classically use sensors to gather geometric information from their surroundings to create a topological map. Integrating AI-based models into robots allows them to extract semantic information from the environment, enabling them to meaningfully map the environment. Once robots can analyze their environment from various perspectives and extract more data, it expands the range of tasks they can perform. There are various strategies to extract semantics from the surroundings, like analyzing objects, patterns, visual aspects of the environment, and human interactions, among others. This article aims to give researchers additional understanding of the most relevant aspects of the semantic mapping process and highlight trends and challenges in the field, providing direction for future research. To achieve this, a thorough literature review was conducted. The PRISMA statement inspired the paper selection process, which included querying, filtering, and selecting papers for this survey. This article provides a comprehensive examination of the semantic mapping process, detailing the standard procedures, common tasks, and significant subfields involved. Particular emphasis is placed on information acquisition techniques, semantic extraction methods, and knowledge representation strategies, including Spatial and Hierarchical approaches. Emerging trends and challenges related to semantic mapping for robotics are identified and discussed, providing context and related works for each. The most significant findings emphasize the importance of semantic mapping in enabling intelligent and adaptive robotic operations in complex environments. The semantic mapping elevates robotic autonomy by enhancing its perception and decision-making process. © 2025, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：