检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Xishuo Zhang, Shan Huang, Yuejiao Ma, Xiao Wang, Zhiyuan Luo, Hongbin State Key Laboratory of Complex & Critical Software Environment Computer Science and Engineering Beihang University Beijing10086 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China

Real-time video analytics services aim to provide users with accurate recognition results timely. However, existing studies usually fall into the dilemma between reducing delay and improving accuracy. The edge computing scenario imposes strict transmission and computation resource constraints, making balancing these conflicting metrics under dynamic network conditions difficult. In this regard, we introduce the age of processed information (AoPI) concept, which quantifies the time elapsed since the generation of the latest accurately recognized frame. AoPI depicts the integrated impact of recognition accuracy, transmission, and computation efficiency. We derive closed-form expressions for AoPI under preemptive and non-preemptive computation scheduling policies w.r.t. the transmission/computation rate and recognition accuracy of video frames. We then investigate the joint problem of edge server selection, video configuration adaptation, and bandwidth/computation resource allocation to minimize the long-term average AoPI over all cameras. We propose an online method, i.e., Lyapunov-based block coordinate descent (LBCD), to solve the problem, which decouples the original problem into two subproblems to optimize the video configuration/resource allocation and edge server selection strategy separately. We prove that LBCD achieves asymptotically optimal performance. According to the testbed experiments and simulation results, LBCD reduces the average AoPI by up to 10.94X compared to state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving CSI Fingerprint Device-Free Localization 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Huang, Tianxin Zhao, Lingjun Dai, Zeyang Lin, Liang Huang, Huakun School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China Greater Bay Area Institue of Precision Medicine Guangzhou China Guangdong Provincial Key Laboratory of Building Energy Efficiency and Application Technologies Guangzhou University Guangzhou China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Device-Free Localization (DFL) method based on wireless signal fingerprint is a mainstream indoor location method at present. The main concerns in this field are location accuracy and complexity of computing, while the problem of privacy protection is easily neglected. Since the leakage of wireless signal data is likely leading to the leakage of location information, this paper proposes a privacy-preserving Channel State Information(CSI) fingerprint device-free localization method based on federated learning(PPDFL). Through federated learning, each client trains a local model using the collected local data and then transmits the trained parameters to the server. The server consolidates these parameters and then distributes the resulting parameters to each client for local model’s updating. After several rounds of training and updating, each client ends up with a fully trained model. Compared with the existing DFL methods, this method would not share the data of each client, and only transmits model parameters between server and client, thus achieving the effect of privacy protection. Several experiments are performed to prove the effectiveness of the proposed PPDFL. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware Contrastive Learning for Selective Classification

arXiv

引用

arXiv 2024年

作者： Wu, Yu-Chang Lyu, Shen-Huan Shang, Haopu Wang, Xiangyu Qian, Chao National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University China College of Computer Science and Software Engineering Hohai University China

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model’s confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement. © 2024, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Learned Video Compression With Refined Adaptive Flow Pyramid And Coordinate-Aware Attention

Learned Video Compression With Refined Adaptive Flow Pyramid...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qian Huang Wenting Liu Xin Li Yiming Wang College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In video compression, motion estimation and motion compensation are critical for achieving efficient encoding. Although the commonly used SpyNet and bilinear interpolation have contributed in improving the compression efficiency, they still have limitations. SpyNet often loses details and fails to fully utilize the feature extraction capabilities of deep networks. Furthermore, bilinear interpolation inherently attenuates high-frequency information, leading to frame blurring and distortion. In this paper, we propose a novel video compression algorithm. To overcome the limitations of SpyNet, we propose a refined adaptive flow pyramid network. This network uses a multi-scale feature pyramid to capture more details. Moreover, we use an iterative cost volume refinement engine that improves the feature representation of the network and iteratively improve the accuracy of motion estimation. In addition, to overcome the limitation of bilinear interpolation, we propose a coordinate-aware attention module, which captures more high-frequency information to improve the accuracy of motion compensation. Experimental results show that our method outperforms VTM-13.2 (LDP) in terms of PSNR.

关键词： Interpolation Adaptive systems Costs Acoustic distortion Accuracy Motion estimation Video compression Feature extraction Motion compensation Speech processing

来源：评论

学校读者我要写书评

暂无评论

Metric localization for lunar rovers via cross-view image matching

引用

Visual Intelligence 2024年第1期2卷 1-14页

作者： Chen, Zihao Li, Kunhong Li, Haoran Fu, Zhiheng Zhang, Hanmo Guo, Yulan School of Electronics and Comunication Engineering the Shenzhen Campus of Sun Yat-sen University Sun Yat-sen University Shenzhen 510275 China Peng Cheng Laboratory Guangdong Shenzhen 518055 China Department of Computer Science and Software Engineering The University of Western Australia Perth 6009 Australia Department of Shanghai Key Laboratory of Aerospace Intelligent Control Technology Shanghai Aerospace Control Technology Institute Shanghai 201109 China College of Electronic Science and Technology National University of Defense Technology Hunan Changsha 410073 China

Accurate localization is critical for lunar rovers exploring lunar terrain features. Traditionally, lunar rover localization relies on sensor data from odometers, inertial measurement units and stereo cameras. However, localization errors accumulate over long traverses, limiting the rover’s localization accuracy. This paper presents a metric localization framework based on cross-view images (ground view from a rover and air view from an orbiter) to eliminate accumulated localization errors. First, we employ perspective projection to reduce the geometric differences in cross-view images. Then, we propose an image-based metric localization network to extract image features and generate a location heatmap. This heatmap serves as the basis for accurate estimation of query locations. We also create the first large-area lunar cross-view image (Lunar-CV) dataset to evaluate the localization performance. This dataset consists of 30 digital orthophoto maps (DOMs) with a resolution of 7 m/pix, collected by the Chang’e-2 lunar orbiter, along with 8100 simulated rover panoramas. Experimental results on the Lunar-CV dataset demonstrate the superior performance of our proposed framework. Compared to the second best method, our method significantly reduces the average localization error by 26% and the median localization error by 22%. © The Author(s) 2024.

关键词： Aerial patch Cross-view metric localization (CVML) Lunar rover Panorama Perspective projection

来源：评论

学校读者我要写书评

暂无评论

NucleiFormer: A Nuclei Segmentation Model Optimized by Joint Haar Wavelet and Adaptive Feature Calibration

NucleiFormer: A Nuclei Segmentation Model Optimized by Joint...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yulin Chen Qian Huang Zhijian Wang Ziyang Yin Meng Geng 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

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Nucleus segmentation plays a vital role in medical image analysis. However, existing segmentation methods frequently encounter hurdles, such as the loss of crucial image details during downsampling and issues like noise and spatial displacement. In this study, we propose NucleiFormer, where Haar wavelet transforms are employed in the encoder to replace conventional downsampling techniques. Additionally, we utilize an adaptive feature calibration module to align and calibrate features of different scales, reduce feature redundancy, suppress noise, and enhance the spatial awareness of the model. Extensive experiments validate our model’s superior segmentation performance in accurately delineating nucleus boundaries and minimizing errors.

关键词： Wavelet transforms Adaptation models Image segmentation Image analysis Noise Termination of employment Calibration Speech processing Optimization Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Spatial Consistency and Feature Diversity Regularization in Transfer Learning for Fine-Grained Visual Categorization

Spatial Consistency and Feature Diversity Regularization in ...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Dai, Zhigang Chen, Junying Mian, Ajmal South China University of Technology Key Laboratory of Big Data and Intelligent Robot Ministry of Education School of Software Engineering Guangzhou China The University of Western Australia Department of Computer Science Perth Australia

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Fine-grained visual categorization is challenged by limited training data by localizing discriminative regions and learning diverse features. We propose an effective regularization method that simultaneously imposes spatial consistency and feature diversity on CNN feature maps from a unified perspective. The former guides different feature map channels to concentrate collaboratively on the discriminative areas while the latter ensures that the feature maps are diverse. The proposed method does not require additional supervision, and leverages the covariance matrix of multi-channel feature maps to regularize the loss at the last convolutional layer where the semantic information is the richest. This allows the influence to be backpropagated to update all convolutional layers. We perform experiments using four network architectures for transfer learning from two source domains to three target domains, and demonstrate that our regularization method improves accuracy in all different settings. The proposed regularization method achieves state-of-the-art performance on CUB-200-2011, Stanford-Cars, and Stanford-Dogs datasets with 89.8%, 94.6%, and 88.5% accuracy, respectively. © 2022 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Blockchain-Based Sharding 7th

An Investigation of Blockchain-Based Sharding

引用

7th International Conference on Smart Computing and Communication, SmartCom 2022

作者： Xiao, Jiahong Liang, Wei Cai, Jiahong Zhu, Hangyu Li, Xiong Xie, Songyou School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan411201 China Guangdong Financial High-Tech Zone "Blockchain +" Fintech Research Institute Foshan528253 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

ISBN: (纸本)9783031281235

Nowadays, blockchain distributed ledger technology is becoming more and more prominent, and its decentralization, anonymization, and tampering obvious features have been widely recognized. These excellent technical features of blockchain have also made it a hot issue for global research. With the wide application of blockchain technology in various industries, some defects are gradually exposed, and more prominently, the blockchain system is unable to meet the current demand of explosive growth of data volume and frequent data interaction. As one of the key technologies to solve this problem, sharding technology is gaining attention. This article introduces common blockchain scaling schemes and focuses on an overview of blockchain sharding. Sharding technology is introduced from two perspectives of intra-slice consensus and inter-slice consensus. The current mainstream slicing technology is summarized according to three different slicing methods: network sharding, transaction sharding, and state sharding. Finally, the challenges faced by current blockchain sharding technology are analyzed and the full text is summarized. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services

Seed Feature Maps-based CNN Models for LEO Satellite Remote ...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Lu, Zhichao Ding, Chuntao Wang, Shangguang Cheng, Ran Juefei-Xu, Felix Boddeti, Vishnu Naresh Sun Yat-sen University School of Software Engineering Zhuhai China Beijing Jiaotong University School of Computer and Information Technology Beijing China Beijing University of Posts and Telecommunications Key Laboratory of Networking and Switching Technology Beijing China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China New York University New YorkNY United States Michigan State University Department of Computer Science and Engineering East LansingMI United States

ISBN: (纸本)9798350304855

Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interest from industry and academia. However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models. Existing approaches often require large floating-point operations (FLOPs) and substantial model parameter transmissions, presenting considerable challenges. To address these issues, this paper introduces a ground-station server-assisted framework. With the proposed framework, each layer of the CNN model contains only one learnable feature map (called the seed feature map) from which other feature maps are generated based on specific rules. The hyperparameters of these rules are randomly generated instead of being trained, thus enabling the generation of multiple feature maps from the seed feature map and significantly reducing FLOPs. Furthermore, since the random hyperparameters can be saved using a few random seeds, the ground station server assistance can be facilitated in updating the CNN model deployed on the LEO satellite. Experimental results on the ISPRS Vaihingen, ISPRS Potsdam, UAVid, and LoveDA datasets for semantic segmentation services demonstrate that the proposed framework outperforms existing state-of-the-art approaches. In particular, the SineFM-based model achieves a higher mIoU than the UNetFormer on the UAVid dataset, with 3.3 × fewer parameters and 2.2 × fewer FLOPs. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Semantic Representation Learning of Scientific Literature Based on Graph Attention Mechanism and Maximum Mutual Information 8

Unsupervised Semantic Representation Learning of Scientific ...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Gao, Hongrui Li, Yawen Liang, Meiyu Guan, Zeli Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing100876 China Beijing University of Posts and Telecommunications School of Economics and Management Beijing100876 China

ISBN: (纸本)9781665477352

Since most scientific literature data are unlabeled, this makes unsupervised graph-based semantic representation learning crucial. Therefore, an unsupervised semantic representation learning method of scientific literature based on graph attention mechanism and maximum mutual information (GAMMI) is proposed. By introducing a graph attention mechanism, the weighted summation of nearby node features makes the weights of adjacent node features entirely depend on the node features. Depending on the features of the nearby nodes, different weights can be applied to each node in the graph. In addition, an unsupervised graph contrastive learning strategy is proposed to solve the problem of being unlabeled and scalable on large-scale graphs. By comparing the mutual information between the positive and negative local node representations on the latent space and the global graph representation, the graph neural network can capture both local and global information. Experimental results demonstrate competitive performance on various node classification benchmarks, achieving good results and sometimes even surpassing the performance of supervised learning. © 2022 IEEE.

关键词： Graph neural networks

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：