检索结果-内蒙古大学图书馆

Visual Class Incremental Learning with Textual Priors Guidance based on an Adapted Vision-Language Model

IEEE Transactions on Multimedia 2025年

作者： Zhang, Wentao Yu, Tong Wang, Ruixuan Xie, Jianhui Trucco, Emanuele Zheng, Wei-Shi Yang, Xiaobo Sun Yat-sen Univerisity School of Computer Science and Engineering Guangzhou510275 China Peng Cheng Laboratory Shenzhen518066 China MOE Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou510275 China Second Affiliated Hospital Guangzhou University of Chinese Medicine State Key Laboratory of Dampness Syndrome of Chinese Medicine Guangzhou510260 China Guangdong Provincial Key Laboratory of Clinical Research on Traditional Chinese Medicine Syndrome Guangzhou510120 China University of Dundee School of Science and Engineering DundeeDD1 4HN United Kingdom

An ideal artificial intelligence (AI) system should have the capability to continually learn like humans. However, when learning new knowledge, AI systems often suffer from catastrophic forgetting of old knowledge. Although many continual learning methods have been proposed, they often ignore the issue of misclassifying similar classes and make insufficient use of textual priors of visual classes to improve continual learning performance. In this study, we propose a continual learning framework based on a pre-trained vision-language model (VLM) that does not require storing old class data. This framework utilizes parameter-efficient fine-tuning of the VLM's text encoder for constructing a shared and consistent semantic textual space throughout the continual learning process. The textual priors of visual classes are encoded by the adapted VLM's text encoder to generate discriminative semantic representations, which are then used to guide the learning of visual classes. Additionally, fake out-of-distribution (OOD) images constructed from each training image further assist in the learning of visual classes. Extensive empirical evaluations on three natural datasets and one medical dataset demonstrate the superiority of the proposed framework. The source code is available at https://***/OpenMedIA/CIL_Adapterd_VLM. © 1999-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

IP2vec:an IP node representation model for IP geolocation

引用

Frontiers of Computer Science 2024年第6期18卷 189-204页

作者： Fan ZHANG Meijuan YIN Fenlin LIU Xiangyang LUO Shuodi ZU State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou 450001China Key Laboratory of Cyberspace Situation Awareness of Henan Province Zhengzhou 450001China

IP geolocation is essential for the territorial analysis of sensitive network entities,location-based services(LBS)and network fraud *** has important theoretical significance and application ***-based IP geolocation is a hot research ***,the existing IP geolocation algorithms cannot effectively utilize the distance characteristics of the delay,and the nodes’connection relation,resulting in high geolocation *** is challenging to obtain the mapping between delay,nodes’connection relation,and geographical *** on the idea of network representation learning,we propose a representation learning model for IP nodes(IP2vec for short)and apply it to street-level IP ***2vec model vectorizes nodes according to the connection relation and delay between nodes so that the IP vectors can reflect the distance and topological proximity between IP *** steps of the street-level IP geolocation algorithm based on IP2vec model are as follows:Firstly,we measure landmarks and target IP to obtain delay and path information to construct the network ***,we use the IP2vec model to obtain the IP vectors from the network ***,we train a neural network to fit the mapping relation between vectors and locations of ***,the vector of target IP is fed into the neural network to obtain the geographical location of target *** algorithm can accurately infer geographical locations of target IPs based on delay and topological proximity embedded in the IP *** cross-validation experimental results on 10023 target IPs in New York,Beijing,Hong Kong,and Zhengzhou demonstrate that the proposed algorithm can achieve street-level *** with the existing algorithms such as Hop-Hot,IP-geolocater and SLG,the mean geolocation error of the proposed algorithm is reduced by 33%,39%,and 51%,respectively.

关键词： IP geolocation network measurement node embedding

来源：评论

学校读者我要写书评

暂无评论

The value of polynomials represented by norm forms

引用

Science China Mathematics 2014年第12期57卷 2525-2528页

作者： WANG Xin State Key Laboratary of Mathematical Engineering and Advanced Computing

Let P(t) be a product of(possibly repeated) linear factors over Q and K/Q an abelian extension. Under a strict condition, we show that the Brauer-Manin obstruction to the Hasse principle and weak approximation is the ... 详细信息

关键词： Brauer group Brauer-Manin obstruction rational point

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Fair Efficiency Comparisons of Decoy-state Quantum key Distribution Protocols

引用

Chinese Journal of Electronics 2018年第2期27卷 241-249页

作者： LI Hongxin GAO Ming YAN Xueping YAN Bao HAN Yu SHAN Ling MA Zhi Information Engineering University State Key Laboratory of Mathematical Engineering and Advanced Computing College of Animal Science and Technology Henan University of Science and Technology

Taking the schemes based on different formulas of secure key rate as examples, we give a fair comparison between typical protocols under Universal composable(UC) security frame. Through analyzing the relationship of security parameters in post-processing stage and final secure key rate, we achieve the unified quantification between protocols based on Gottesman-Lo-L¨utkenhausPreskill(GLLP) formula and the ones under UC *** on the above research, the impact of different sending lengths and secure parameters on secure key rate is investigated. Besides, we analyze the conditions of fair comparison, and for the first time we give a fair comparison between the protocols based on GLLP formula and smooth entropy. By typical efficiency comparisons, we summarize the way for improving secure key rate in the light intensity choice and the single bit error rate estimation method.

关键词： Quantum key distribution(QKD) Finite-key Universal composable(UC) Fair comparison

来源：评论

学校读者我要写书评

暂无评论

A new aggregate signature scheme in cryptographic currency

引用

International Journal of Performability engineering 2017年第5期13卷 754-762页

作者： Yuan, Chao Xu, Mixue Si, Xueming State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Zhengzhou450001 China

With the rise of Bitcoin, cryptographic currencies have attracted more and more attention. Subsequently, other cryptographic currencies were gradually created, such as Zcash, Moreno, Dash and so on. In cryptographic currency, privacy preserving and expansion are two key technical points. In terms of privacy preserving, more effective solutions were proposed in Zcach, Moreno, Dash and other cryptographic currencies systems, in which ring signature, zero knowledge proof and other cryptographic techniques played important roles. But these schemes mainly considered protecting the addresses of both sides of the transaction. In terms of expansion, lightning network and other projects also give solutions. But most of these projects will bring other problems. In this paper, a signature scheme based on the aggregate signature and the elliptic curve algorithm is proposed to hide the transaction value of a single sender and receiver in the transactions which contain multiple inputs and outputs. This signature scheme achieves the purpose of privacy preserving from the transaction value. Further, the correctness proof and security analysis are given in this paper. In addition to that, another signature scheme that combines aggregation signature with bilinear ring signature is proposed. This aggregate ring signature scheme gives another attempt to solve the problem of expansion in the cryptographic currency system only using cryptographic technologies. At the same time, the sender's addresses can be hidden. Similarly, we also confirmed the correctness of this signature scheme.

关键词： Expansion

来源：评论

学校读者我要写书评

暂无评论

IP-geolocater:a more reliable IP geolocation algorithm based on router error training

引用

Frontiers of Computer Science 2022年第1期16卷 101-111页

作者： Shuodi ZU Xiangyang LUO Fan ZHANG State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001China Zhengzhou Science and Technology Institute Zhengzhou450001China

Location based services(LBS)are widely utilized,and determining the location of users’IP is the foundation for *** by unstable delay and insufficient landmarks,the existing geolocation algorithms have problems such as low geolocation accuracy and uncertain geolocation error,difficult to meet the requirements of LBS for accuracy and reliability.A new IP geolocation algorithm based on router error training is proposed in this manuscript to improve the accuracy of geolocation results and obtain the current geolocation error ***,bootstrapping is utilized to divide the landmark data into training set and verification set,and/24 subnet distribution is utilized to extend the training ***,the path detection is performed on nodes in the three data sets respectively to extract the metropolitan area network(MAN)of the target city,and the geolocation result and error of each router in MAN are obtained by training the detection ***,the MAN is utilized to get the target’s *** on China’s 24,254 IP geolocation experiments,the proposed algorithm has higher geolocation accuracy and lower median error than existing typical geolocation algorithms LBG,SLG,NNG and RNBG,and in most cases the difference is less than 10km between estimated error and actual error.

关键词： estimated error geolocation path detection network measurement

来源：评论

学校读者我要写书评

暂无评论

A Formalization Research on Web Server and Scheduling Strategy for Heterogeneity

A Formalization Research on Web Server and Scheduling Strate...

引用

2016 IEEE advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Bolin Ma Zheng Zhang Yongsheng Zhu State key Laboratory of Mathematical Engineering And Advanced Computing MEAC

ISBN: (纸本)9781509001668

Most web service systems are built in a static configuration web server or re dundant same web ***,traditional web service system make it easy for a cyber adversary to plan and launch *** improve the cyber security,mimic security defense where heterogeneity play an important role has been proposed to increase the difficulty for the adversary to launch successful *** this paper,we first present a formal description of heterogeneous web servers and a method how to measure the heterogeneity of web *** addition,we also present the scheduling strategy for heterogeneous web servers and demonstrate the effectiveness of this strategy in a general heterogeneous web service *** strategy of heterogeneous web servers scheduling can disrupt the vicious scan,deceive the judgment about vulnerability and prevent some vulnerabilities being found that make vulnerability attacks difficult.

关键词： Cyb er Security Heterogeneity Scheduling Strategy

来源：评论

学校读者我要写书评

暂无评论

Parallelizing Sparse LU Decomposition on FPGAs

Parallelizing Sparse LU Decomposition on FPGAs

引用

11th International Conference on Field-Programmable Technology (FPT)

作者： Wu, Guiming Xie, Xianghui Dou, Yong Sun, Junqing Wu, Dong Li, Yuan State Key Laboratory of Mathematical Engineering and Advanced Computing China

ISBN: (纸本)9781467328463;9781467328449

Sparse LU decomposition is the core computation in the direct method that solves sparse systems of linear equations. Only little work has been conducted on parallelizing it on FPGAs. In this paper, we study parallelization strategies for sparse LU decomposition on FPGAs. We first analyze how to parallelize the right-looking algorithm and find that this algorithm is not suitable for FPGAs. Then the left-looking algorithm is analyzed and considered as better candidate than the right-looking version. Our design derived from the left-looking algorithm is based on a simple yet efficient parallel computational model for FPGAs. Our design mainly consists of multiple parallel processing elements (PEs). A total of 14 PEs can be integrated into a Xilinx Virtex-5 XC5VLX330. Unlike related work, where their designs are applied to sparse matrices from particular application domains, our hardware design can be applied to any symmetric positive definite or diagonally dominant matrices.

关键词： Sparse matrices Random access memory Algorithm design and analysis Parallel processing Field programmable gate arrays Matrix decomposition Hardware

来源：评论

学校读者我要写书评

暂无评论

QUANTUM COLLISION SEARCH ALGORITHM AGAINST NEW FORK-256

引用

Journal of Electronics(China) 2014年第4期31卷 366-370页

作者： Du Fangwei Wang Hong Ma Zhi State Key Laboratory of Mathematical Engineering and Advanced Computing

In order to improve the attack efficiency of the New FORK-256 function, an algorithm based on Grover's quantum search algorithm and birthday attack is proposed. In this algorithm, finding a collision for arbitrary hash function only needs O(2m/3) expected evaluations, where m is the size of hash space value. It is proved that the algorithm can obviously improve the attack efficiency for only needing O(2 74.7) expected evaluations, and this is more efficient than any known classical algorithm, and the consumed space of the algorithm equals the evaluation.

关键词： Quantum computation Quantum collision Grover's search algorithm New FORK-256CLC number:TN918.1

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：