检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yang, Jianan Gao, Chenchao Xiao, Zhiqing Zhao, Junbo Wu, Sai Chen, Gang Wang, Haobo College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China School of Software Technology Zhejiang University China International School of Information Science and Engineering Dalian University of Technology China

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPipe: Pipeline Inference Framework with High-quality Offline Parallelism Planning for Heterogeneous Edge Devices 24

EPipe: Pipeline Inference Framework with High-quality Offlin...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Xiong, Yi Liu, Weihong Zhang, Rui Zu, Yulong Zhu, Zongwei Zhou, Xuehai School of Computer Science and Technology University of Science and Technology of China China Suzhou Institute for Advanced Research University of Science and Technology of China China School of Software Engineering University of Science and Technology of China China

ISBN: (纸本)9798400710773

Pipeline parallelism is essential for edge computing as it effectively consolidates the limited resources of edge devices, enabling the deployment of large Deep Neural Network (DNN) models and accelerating inference processes without compromising the performance of models. Accurate computation and communication latency estimation on heterogeneous edge devices is essential for searching for a superior parallelism plan. However, existing heterogeneous pipeline inference approaches either incur substantial resource wastage during online parallelism planning, as they utilize profiling strategies that occupy physical devices;or rely on cost models with inadequate representational capabilities, leading to inaccurate predictions, thereby harming the result of pipeline planning. This paper proposes EPipe, a novel pipeline inference framework that supports high-quality offline planning in heterogeneous edge environments. EPipe integrates two core components: the Task-Device Co-analyzer (TDC) and the Multi-pipeline Parallelism Planner (MPP). TDC utilizes an undirected connected graph to depict the compatibility of DNNs across device groups and precisely estimates inference and communication latencies through fine-grained modeling. Based on TDC, MPP utilizes a dynamic programming-based genetic algorithm to explore multi-pipeline solutions, extending beyond traditional single-pipeline methods. A comprehensive experimental evaluation on an edge testbed confirms the effectiveness of EPipe, demonstrating significant speedups in inference tasks for both task streams and single tasks. © 2024 Copyright is held by the owner/author(s).

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Crysformer:An attention-based graph neural network for properties prediction of crystals

引用

Chinese Physics B 2023年第9期32卷 15-20页

作者：王田陈家辉滕婧史金钢曾新华 Hichem Snoussi Institute of Artificial Intelligence SKLSDEBeihang UniversityBeijing 100191China Zhongguancun Laboratory Beijing 100191China School of Aeronautic Science and Engineering Beihang UniversityBeijing 100191China School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China School of Software Engineering Xi'an Jiaotong UniversityXi'an 710049China Academy for Engineering and Technology Fudan UniversityShanghai 200433China Charles Delaunay Institute University of Technology of TroyesTroyes Cedex 10004France

We present a novel approach for the prediction of crystal material properties that is distinct from the computationally complex and expensive density functional theory(DFT)-based ***,we utilize an attention-based graph neural network that yields high-accuracy *** approach employs two attention mechanisms that allow for message passing on the crystal graphs,which in turn enable the model to selectively attend to pertinent atoms and their local environments,thereby improving *** conduct comprehensive experiments to validate our approach,which demonstrates that our method surpasses existing methods in terms of predictive *** results suggest that deep learning,particularly attention-based networks,holds significant promise for predicting crystal material properties,with implications for material discovery and the refined intelligent systems.

关键词： deep learning property prediction crystal attention networks

来源：评论

学校读者我要写书评

暂无评论

An Overview of Security Threats, Attack Detection and Defense for Large-Scale Multi-Agent Systems (LSMAS) in Internet of Things (IoT)

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 70-81页

作者： Cai, Jijing Wen, Long Feng, Hailin Fang, Kai Chen, Junxin Wei, Wei Wang, Wei Zhejiang A and F University College of Mathematics and Computer Science Hangzhou311300 China Macau University of Science and Technology School of Innovation Engineering Macau999078 China Dalian University of Technology School of Software Dalian116621 China Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Beijing Institute of Technology School of Medical Technology Beijing100081 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Shenzhen518172 China

With the global advancement of the Internet of Things (IoT), large-scale multi-agent systems (LSMAS) technology has been increasingly adopted across various industries. Despite the widespread use of IoT, vulnerabilities in its software and hardware components pose significant challenges to ensuring security. To address the security concerns faced by LSMAS, this article explores its application in IoT domains such as smart grids, smart manufacturing, and smart healthcare. By examining the structural layers of IoT-the perception layer, network layer, and application layer-this paper analyzes the specific security threats encountered by each layer, along with the defense strategies designed to counter these attacks. Furthermore, we categorize and compare both traditional and AI-based attack detection methods, dividing the latter into machine learning-based, deep learning-based, and transfer learning-based approaches. This analysis highlights the strengths and weaknesses of the various attack detection methods currently deployed in LSMAS, identifying the existing challenges they face. Finally, we outline potential trends for the future development of LSMAS in IoT, offering research directions for experts in related fields. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A survey for light field super-resolution

引用

High-Confidence Computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

来源：评论

学校读者我要写书评

暂无评论

A Cost-Efficient Anonymous Authenticated and Key Agreement Scheme for V2I-Based Vehicular Ad-Hoc Networks

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第9期25卷 12621-12630页

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Shamshad, Salman Alenazi, Mohammed J. F. Das, Ashok Kumar University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518000 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500032 India

The rise of smart cities is directly connected to the increasing use of vehicles. The growing vehicle utilization has driven the emergence of Vehicular Ad-hoc Networks (VANETs), facilitating instant information exchange among vehicles. The system provides essential information regarding road conditions, traffic patterns, and more relevant data. VANETs encompass two fundamental categories of communication exchanges, namely Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I). V2I technology facilitates the integration of cars and transportation infrastructure, enabling effective communication between vehicles and infrastructure. Nevertheless, the potential of V2I communication has various security concerns arising from prevalent security threats. Current authentication techniques encounter challenges regarding complexity, security, and privacy considerations. We designed a hash-based lightweight and anonymous authentication scheme to address the aforementioned restrictions and enhance the effectiveness of authentication in V2I architecture. This scheme effectively combines identity, password, and bio-metric to enhance resistance against impersonation, denial of service, and privileged insider attacks. The devised scheme distinguishes itself by a comparative analysis and security proofs, highlighting its superior capability in guaranteeing secure authentication in V2I communication. The comprehensive security analysis conducted formally and informally showcases the robustness of the proposed solution against several threats. The performance evaluation results show that our scheme demonstrates a decrease in the computational cost of 51.40% approximately and a reduction in communication overhead of around 22.57%. These results establish the efficiency and scalability of the proposed scheme as a viable solution for V2I architecture. © 2000-2011 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Survey on digital twins for Internet of Vehicles:Fundamentals,challenges,and opportunities

引用

Digital Communications and Networks 2024年第2期10卷 237-247页

作者： Jiajie Guo Muhammad Bilal Yuying Qiu Cheng Qian Xiaolong Xu Kim-Kwang Raymond Choo School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Department of Computer Engineering Hankuk University of Foreign StudiesGyeonggi-do17035South Korea Jiangsu Hydraulic Research Institute Nanjing210044China Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

As autonomous vehicles and the other supporting infrastructures(e.g.,smart cities and intelligent transportation systems)become more commonplace,the Internet of Vehicles(IoV)is getting increasingly *** have been attempts to utilize Digital Twins(DTs)to facilitate the design,evaluation,and deployment of IoV-based systems,for example by supporting high-fidelity modeling,real-time monitoring,and advanced predictive ***,the literature review undertaken in this paper suggests that integrating DTs into IoV-based system design and deployment remains an understudied *** addition,this paper explains how DTs can benefit IoV system designers and implementers,as well as describes several challenges and opportunities for future researchers.

关键词： Internet of vehicles Digital twin Simulation Traffic systems

来源：评论

学校读者我要写书评

暂无评论

Lightweight Protective Clothing Detection Algorithm Based on Ghost Convolution and GSConv Convolution

Lightweight Protective Clothing Detection Algorithm Based on...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Qianjun Guan Kun Yu Haoran Wang Qiangqiang Li Shihong Gao Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai’an Jiangsu China

GhostNet is proposed by Huawei Noah’s Ark Laboratory in CVPR2020, which can be used with the same accuracy, with less speed and less computation than SOTA method. This convolution is a low-cost operation used to decrease the amount of computation and related parameters. Ghost convolution can be used as an alternative to traditional convolution operations because they have the same accuracy. However, utilize significantly less computation and a much smaller parameter count. GSConv(Group-Shared Convolution) is a convolution operation based on group shared weights. This operation achieves efficient parallel convolution operations by grouping convolution kernels. In this way, the parameters used and calculation complexity of the model can be reduced to some extent. This makes the network more computationally efficient and smaller in model size while maintaining accuracy. The algorithm can detect the location of protective clothing quickly and efficiently, and its accuracy and efficiency have been verified. Because the algorithm adopts lightweight network structure, real-time detection can be realized on lowpower devices efficiently. The model architecture enhances the performance based on the YOLOv5 target detection algorithm by incorporating additional features. So that the model can maintain a high precision, which is crucial for the protective clothing detection algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

引用

Machine Intelligence Research 2023年第4期20卷 554-568页

作者： Mengya Han Yibing Zhan Baosheng Yu Yong Luo Han Hu Bo Du Yonggang Wen Dacheng Tao School of Computer Science National Engineering Research Center for Multimedia SoftwareWuhan UniversityWuhan430072China Hubei Luojia Laboratory Wuhan430072China School of Computer Science The University of SydneySydney2006Australia JD Explore Academy Beijing101116China School of Information and Electronics Beijing Institute of TechnologyBeijing100081China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.

关键词： Few-shot learning metric-based meta learning concept learning region-adaptive concept-aggregation

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Covid-19 Twitter Data using Deep Learning Algorithm 2

Sentiment Analysis of Covid-19 Twitter Data using Deep Learn...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Valarmathi, B. Gupta, N. Srinivasa Karthick, V. Chellatamilan, T. Santhi, K. Chalicheemala, Dhanush Department of Software and Systems Engineering School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Manufacturing School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Assistant Systems Engineer Tata Consultancy Services Chennai India Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Information Technology School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

A key method used in the study of Natural Language Processing (NLP) is sentiment analysis, or emotion analysis, plays a pivotal role in text analysis. Its primary function is to discern and categorize the underlying emotions within textual content, classifying them as positive, neutral, or negative sentiments. A variety of textual inputs can be used with this process, including entire documents, individual sentences, and more. Understanding the sentiments expressed by individuals is of paramount importance to organizations in today's digital age. Clients and customers now have the means to express their thoughts and emotions with greater ease and immediacy than ever before. This wealth of sentiment data can offer valuable insights that organizations can leverage to enhance their products, services, and overall customer experience. The present study focuses on the sentiment analysis of Twitter data related to the COVID-19 pandemic, employing the Long Short-Term Memory (LSTM) algorithm. To improve the accuracy of sentiment analysis, a pre-processing procedure is introduced, which involves the use of the Neat Text module in Python to clean the tweets. In this research endeavor, a dataset comprising 1,79,107 COVID-19-related tweets is subjected to sentiment analysis using the proposed pre-processing module and LSTM. The results demonstrate an impressive accuracy rate of 96% in accurately determining the sentiments conveyed in these COVID-19 tweets. In contrast, the existing algorithm, based on Artificial Neural Network (ANN), achieved a significantly lower accuracy rate of 76%. This research not only showcases the effectiveness of LSTM and pre-processing in sentiment analysis but also highlights the significance of sentiment analysis in gaining valuable insights from vast amounts of textual data, especially when important events like the COVID-19 pandemic are involved. © 2024 Elsevier B.V.. All rights reserved.

关键词： COVID-19

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：