检索结果-内蒙古大学图书馆

Building connectome analysis tools with representation learning on neuronal skeleton and circuit topology

Neural networks 2025年 190卷 107603页

作者： Minghui Liao Guojia Wan Wenbin Hu Bo Du School of Computer Science Wuhan University Wuhan China National Engineering Research Center for Multimedia Software Wuhan University Wuhan China Institute of Artificial Intelligence Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Analyzing connectome plays a significant role in the investigation of neurological diseases and brain research. However, the efficiency of utilizing anatomical, physiological, or molecular characteristics of neurons is relatively low and costly. With the advancements in volume electron microscopy(VEM) and analysis techniques for brain tissue, we are able to obtain whole-brain connectome consisting neuronal high-resolution morphology and connectivity information. Nevertheless, few tools are built based on such data for automated connectome analysis. In this paper, we introduce a connectome analysis tool based on a representation learning model termed NeuNet. NeuNet consists of three key components: Connectome Encoder, Skeleton Encoder, and Readout Layer, which together integrate information pertaining to neuronal connectivity and morphology. Furthermore, we reprocess and release a brain neuron reconstruction dataset from a Drosophila Nerve Cord VEM data. We apply the proposed tool to tasks related to connectome analysis, including neuron classification, brain circuit layout, neuron retrieval and neuron morphology description, and the experiments demonstrate the effectiveness of our tool. We will soon release our code and data on https://***/WHUminghui/ConnectomeAnalysisTool .

关键词： Brain circuit Neuron reconstruction Connectome analysis Graph neural network Neuron morphology

来源：评论

学校读者我要写书评

暂无评论

Channel Augmented Joint Learning for Visible-Infrared Recognition

Channel Augmented Joint Learning for Visible-Infrared Recogn...

引用

International Conference on computer Vision (ICCV)

作者： Mang Ye Weijian Ruan Bo Du Mike Zheng Shou National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China National University of Singapore Singapore

ISBN: (纸本)9781665428132

This paper introduces a powerful channel augmented joint learning strategy for the visible-infrared recognition problem. For data augmentation, most existing methods directly adopt the standard operations designed for single-modality visible images, and thus do not fully consider the imagery properties in visible to infrared matching. Our basic idea is to homogenously generate color-irrelevant images by randomly exchanging the color channels. It can be seamlessly integrated into existing augmentation operations without modifying the network, consistently improving the robustness against color variations. Incorporated with a random erasing strategy, it further greatly enriches the diversity by simulating random occlusions. For cross-modality metric learning, we design an enhanced channel-mixed learning strategy to simultaneously handle the intra-and cross-modality variations with squared difference for stronger discriminability. Besides, a channel-augmented joint learning strategy is further developed to explicitly optimize the outputs of augmented images. Extensive experiments with insightful analysis on two visible-infrared recognition tasks show that the proposed strategies consistently improve the accuracy. Without auxiliary information, it improves the state-of-the-art Rank-1/mAP by 14.59%/13.00% on the large-scale SYSU-MM01 dataset.

关键词： Measurement computer vision Image color analysis Robustness Task analysis Standards

来源：评论

学校读者我要写书评

暂无评论

LocalDrop: A hybrid regularization for deep neural networks

arXiv

引用

arXiv 2021年

作者： Lu, Ziqing Xu, Chang Du, Bo Ishida, Takashi Zhang, Lefei Sugiyama, Masashi The National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430079 China The School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia RIKEN Center for Advanced Intelligence Project Department of Complexity Science and Engineering Graduate School of Frontier Sciences The University of Tokyo Japan

In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas. We propose a new approach for the regularization of neural networks by the local Rademacher complexity called LocalDrop. A new regularization function for both fully-connected networks (FCNs) and convolutional neural networks (CNNs), including drop rates and weight matrices, has been developed based on the proposed upper bound of the local Rademacher complexity by the strict mathematical deduction. The analyses of dropout in FCNs and DropBlock in CNNs with keep rate matrices in different layers are also included in the complexity analyses. With the new regularization function, we establish a two-stage procedure to obtain the optimal keep rate matrix and weight matrix to realize the whole training model. Extensive experiments have been conducted to demonstrate the effectiveness of LocalDrop in different models by comparing it with several algorithms and the effects of different hyperparameters on the final performances. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Ensembling GAN for Cross-Domain Semantic Segmentation

arXiv

引用

arXiv 2021年

作者： Xu, Yonghao He, Fengxiang Du, Bo Tao, Dacheng Zhang, Liangpei The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China Vienna1030 Austria JD Explore Academy *** Inc. Beijing100176 China School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430079 China

Deep neural networks (DNNs) have greatly contributed to the performance gains in semantic segmentation. Nevertheless, training DNNs generally requires large amounts of pixel-level labeled data, which is expensive and time-consuming to collect in practice. To mitigate the annotation burden, this paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN. Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model, the latter of which is a common barrier shared by most adversarial training-based methods. We theoretically analyze SE-GAN and provide an O(1/√N) generalization bound (N is the training sample size), which suggests controlling the discriminator's hypothesis complexity to enhance the generalizability. Accordingly, we choose a simple network as the discriminator. Extensive and systematic experiments in two standard settings demonstrate that the proposed method significantly outperforms current state-of-the-art approaches. The source code of our model is available online (https://***/YonghaoXu/SE-GAN). Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Tigc-Net: Transformer-Improved Graph Convolution network for Spatio-Temporal Prediction

SSRN

引用

SSRN 2022年

作者： Chen, Kai Yang, Chunfeng Zhou, Zhengyuan Liu, Yao Ji, Tianjiao Sun, Weiya Chen, Yang School of Cyber Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China The College of Software Engineering Southeast University Nanjing210096 China Laboratory of Image Science and Technology The School of Computer Science and Engineering Southeast University Nanjing210096 China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of Radiology Zhongda Hospital Southeast University Nanjing210009 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing210096 China NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention Beijing China Beijing Institute of Tracking and Communication Technology Beijing100094 China

Modeling spatio-temporal sequences is an important topic yet challenging for existing neural networks. Most of the current spatio-temporal sequence prediction methods usually capture features separately in temporal and spatial dimensions or employ multiple mutually independent local spatio-temporal graphs to represent a spatio-temporal sequence. The first kind of method mentioned above is difficult to mine the complex spatio-temporal correlations, while the other is limited for the accuracy of long-term predictions. To handle these issues, this paper proposes a Transformer-Improved Graph Convolution network for spatio-temporal prediction. Specifically, the temporal location encoding method is exploited to derive the spatio-temporal characteristics of the sequence utilizing a spatio-temporal feature fusion network. In addition, a spatio-temporal attention network is developed to enhance the spatio-temporal correlation of the sequence, and the dynamic spatial features of sequence are further extracted through the adaptive graph convolution network. A private dataset and a public dataset are employed to demonstrate the performance of the proposed TIGC-Net. The qualitative and quantitative results show that the proposed TIGC-Net can extract dynamic spatiotemporal properties more effectively, enhance the spatio-temporal correlation of sequences and improve the prediction accuracy compared with four stateof-the-art. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Towards 6G wireless communication networks:vision, enabling technologies, and new paradigm shifts

引用

Science China(Information Sciences) 2021年第1期64卷 5-78页

作者： Xiaohu YOU Cheng-Xiang WANG Jie HUANG Xiqi GAO Zaichen ZHANG Mao WANG Yongming HUANG Chuan ZHANG Yanxiang JIANG Jiaheng WANG Min ZHU Bin SHENG Dongming WANG Zhiwen PAN Pengcheng ZHU Yang YANG Zening LIU Ping ZHANG Xiaofeng TAO Shaoqian LI Zhi CHEN Xinying MA Chih-Lin I Shuangfeng HAN Ke LI Chengkang PAN Zhimin ZHENG Lajos HANZO Xuemin (Sherman) SHEN Yingjie Jay GUO Zhiguo DING Harald HAAS Wen TONG Peiying ZHU Ganghua YANG Jun WANG Erik G.LARSSON Hien Quoc NGO Wei HONG Haiming WANG Debin HOU Jixin CHEN Zhe CHEN Zhangcheng HAO Geoffrey Ye LI Rahim TAFAZOLLI Yue GAO H.Vincent POOR Gerhard P.FETTWEIS Ying-Chang LIANG National Mobile Communications Research Laboratory School of Information Science and EngineeringSoutheast University Purple Mountain Laboratories Shanghai Institute of Fog Computing Technology (SHIFT) ShanghaiTech University Research Center for Network Communication Peng Cheng Laboratory State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications National Engineering Laboratory for Mobile Network Technologies Beijing University of Posts and Telecommunications National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of China (UESTC) China Mobile Research Institute School of Electronics and Computer Science University of Southampton Department of Electrical and Computer Engineering University of Waterloo Global Big Data Technologies Centre (GBDTC) University of Technology Sydney School of Electrical and Electronic Engineering The University of Manchester LiFi Research and Development Centre Institute for Digital CommunicationsSchool of EngineeringThe University of Edinburgh Huawei Technologies Canada Co. Ltd. Huawei Technologies Department of Electrical Engineering (ISY) Link?ping University Institute of Electronics Communications & Information Technology (ECIT)Queen's University Belfast State Key Laboratory of Millimeter Waves School of Information Science and EngineeringSoutheast University School of Electrical and Computer Engineering Georgia Institute of Technology 5G Innovation Centre University of Surrey Princeton University Vodafone Chair Mobile Communications Systems Technische Universit?t Dresden Center for Intelligent Networking and Communications (CINC) University of Electronic Science and Technology of China (UESTC)

The fifth generation(5G) wireless communication networks are being deployed worldwide from 2020 and more capabilities are in the process of being standardized, such as mass connectivity, ultra-reliability,and guaranteed low latency. However, 5G will not meet all requirements of the future in 2030 and beyond, and sixth generation(6G) wireless communication networks are expected to provide global coverage, enhanced spectral/energy/cost efficiency, better intelligence level and security, etc. To meet these requirements, 6G networks will rely on new enabling technologies, i.e., air interface and transmission technologies and novel network architecture, such as waveform design, multiple access, channel coding schemes, multi-antenna technologies, network slicing, cell-free architecture, and cloud/fog/edge computing. Our vision on 6G is that it will have four new paradigm shifts. First, to satisfy the requirement of global coverage, 6G will not be limited to terrestrial communication networks, which will need to be complemented with non-terrestrial networks such as satellite and unmanned aerial vehicle(UAV) communication networks, thus achieving a space-airground-sea integrated communication network. Second, all spectra will be fully explored to further increase data rates and connection density, including the sub-6GHz, millimeter wave(mmWave), terahertz(THz),and optical frequency bands. Third, facing the big datasets generated by the use of extremely heterogeneous networks, diverse communication scenarios, large numbers of antennas, wide bandwidths, and new service requirements, 6G networks will enable a new range of smart applications with the aid of artificial intelligence(AI) and big data technologies. Fourth, network security will have to be strengthened when developing 6G networks. This article provides a comprehensive survey of recent advances and future trends in these four aspects. Clearly, 6G with additional technical requirements beyond those of 5G will enable f

关键词： 6G vision network architecture air interface and transmission technologies space-air-ground-sea integrated network all spectra artificial intelligence network security

来源：评论

学校读者我要写书评

暂无评论

From hippocampal neurons to broad spiking neural networks

引用

Neurocomputing 2025年 647卷

作者： Yaodong Wang Yiping Zuo Dan Chen Weiping Tu Albert Y. Zomaya Xiaoli Li National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan 430072 China School of Computer Science The University of Sydney Sydney NSW Australia State Key Laboratory of Cognitive Neuroscience and Learning Faculty of Psychology Beijing Normal University Beijing 100875 China

Spiking Neural network (SNN) provides an irreplaceable mechanism for series prediction, particularly in scenarios where time and computing resources are both critical, exhibiting superiority over other deep learning models with sparse and spike-based communication inherent to SNN methods. However, as the depth of the network increases, a critical challenge arises: excessive diffusion of signals in the deeper network can seriously affect its accuracy and efficiency. Inspired by the organizational principles of hippocampal circuits, this study proposes a broad learning framework inspired by the brain ( B 2 L ), offering an alternative SNN architecture to mitigate the problem of excessive diffusion. It adopts a broad, incrementally extendable structure while adopting sparse coding for data representation, dedicated to: (1) Construction of the B 2 L SNN : Combining preliminary feature extraction with enhancement processing, a dual-layer broad structure establishes random vector functional-link (RVFL) mapping between rate-coded spike sequences and output labels, effectively preventing excessive diffusion to upstream neurons; (2) Extendable Optimization of B 2 L SNN : Drawing from the concept of incremental learning, B 2 L SNN employs a weight optimization method to search for optimal configurations by expanding RVFL mappings from initial architecture to static datasets through incremental neuron integration. Experiments across six benchmarks (MNIST, CIFAR-10, CIFAR-100, NORB, N-MNIST, and BCI IV 2b) demonstrate: (1) B 2 L SNN achieves 20.3×faster training time than four SNN variants (4058 seconds → 197 s) via random vector functional-link mapping; (2) 96.97% NORB accuracy (+3.64% over SNN2ANN) with 2.79 ms inference time (3.06×speedup), also achieving SOTA 89.52% accuracy on BCI IV 2b and leading N-MNIST inference speed (3.85ms); (3) Scalability: With 1.5×expansion in feature layers (PF: 60 → 100, EF: 7k → 11k), B 2 L SNN achieves 1.04% accuracy improvement on MNIST alon

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation

arXiv

引用

arXiv 2021年

作者： Peng, Yang Liu, Ping Luo, Yawei Zhou, Pan Xu, Zichuan Liu, Jingen Center for Frontier AI Research Agency for Science Technology and Research Singapore Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan China College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Liaoning Dalian China

Unsupervised domain adaptive person re-identification has received significant attention due to its high practical value. In past years, by following the clustering and finetuning paradigm, researchers propose to utilize the teacher-student framework in their methods to decrease the domain gap between different person re-identification datasets. Inspired by recent teacher-student framework based methods, which try to mimic the human learning process either by making the student directly copy behavior from the teacher or selecting reliable learning materials, we propose to conduct further exploration to imitate the human learning process from different aspects, i.e., adaptively updating learning materials, selectively imitating teacher behaviors, and analyzing learning materials structures. The explored three components, collaborate together to constitute a new method for unsupervised domain adaptive person re-identification, which is called Human Learning Imitation framework. The experimental results on three benchmark datasets demonstrate the efficacy of our proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A convolutional neural network-based diagnostic method using resting-state electroencephalograph signals for major depressive and bipolar disorders

引用

Biomedical Signal Processing and Control 2022年第PartB期72卷 103370-103370页

作者： Lei, Yu Belkacem, Abdelkader Nasreddine Wang, Xiaotian Sha, Sha Wang, Changming Chen, Chao Beijing Institute of Basic Medical Sciences Beijing China Department of Computer and Network Engineering College of Information Technology United Arab Emirates University Al Ain United Arab Emirates School of Artificial Intelligence Xidian University Xian China National Clinical Research Center for Mental Disorders & Beijing Key Laboratory of Mental Disorders Beijing Anding Hospital Capital Medical University Beijing China Brain-inspired Intelligence and Clinical Translational Research Center/Department of Neurosurgery Xuanwu Hospital Capitap Medical University Beijing China Key Laboratory of Complex System Control Theory and Application Tianjin University of Technology China Academy of Medical Engineering and Translational Medicine Tianjin University Tianjin China

Background: Early and accurate diagnosis of bipolar and major depressive disorders is important in clinical practice. However, no diagnostic biomarkers can discriminate bipolar from major depressive disorder with high accuracy at present. Methods: We propose a novel convolutional neural network architecture using multichannel raw resting-state electroencephalograph signals to differentiate bipolar disorder from major depressive disorder. This method has great potential in diagnosing mental disorders. In total, 101 patients with major depressive disorder, 82 patients with bipolar disorder, and 81 healthy controls were assessed. Clinical diagnosis was performed by psychiatrists based on the Diagnostic and Statistical Manual of Mental Disorders, fifth edition. Participants were instructed to fix their eyes on a cross on the monitor during the collection of resting-state electroencephalograph signals. Results: A classification mean accuracy of 96.88% was achieved using the resting-state electroencephalograph signals with the 10-fold cross-validation method. The results indicate that deep neural networks could learn efficient feature patterns automatically without manual feature selections. Both statistical analysis and feature visualization on different brain regions showed that the classification performance and the learned features of the proposed model were consistent with that obtained in neurobiological studies on bipolar and major depressive disorders. Conclusions: The combined use of deep neural networks and electroencephalograph signals is an effective approach for the computer-aided diagnosis of bipolar and major depressive disorders. © 2021 Elsevier Ltd

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Improved Online Multiple Pedestrian Tracking Based on Head and Body Detection

An Improved Online Multiple Pedestrian Tracking Based on Hea...

引用

International Conference on Mobile Ad-hoc and Sensor networks, MSN

作者： Zhihong Sun Jun Chen Mithun Mukherjee Haihui Wang Dang Zhang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China School of Computer Science and Technology Wuhan Institute of Technology Wuhan Hubei China School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9781665406697

Multiple Object Tracking (MOT) is an important computer vision task which has gained increasing attention due to its academic and commercial potential. Although many researchers have proposed effective method, they failed in crowd scene. The reason is that body detection and tracking is used in existing MOT methods. In crowd scene, many detections are missed detect and many overlap body bounding boxes decrease the quality of data association. To handle this issue, this paper propsed an online novel multiple pedestrians tracking, which is based on head detection. We first fuse the head and body detection to improve the detection result. Then, we use the head detection bounding box to replace the body detection bounding box for tracking. Finally, the experimental results demonstrate the effectiveness of our proposed method and achieve best performance with the state-of-the-art MOT trackers.

关键词： computer vision Fuses Benchmark testing Sensors Object tracking Task analysis

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：