检索结果-内蒙古大学图书馆

作者： Xie, Gengsheng Wen, Xianbin Yuan, Liming Wang, Jianchen Guo, Changlun Jia, Yansong Li, Minghao School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China

Learning distinguishing features from training datasets while filtering features of occlusions is critical to person retrieval scenarios. Most of the current person re-identification (Re-ID) methods based on classification or deep metric representation learning tend to overlook occlusion issues on the training set. Such representations from obstacles are easily over-fitted and misleading due to being considered as a part of the human body. To alleviate the occlusion problem, we propose a pose-guided feature region-based fusion network (PFRFN), to utilize pose landmarks as guidance to guide local learning for a good property of local feature, and the representation learning risk is evaluated on each part loss separately. Compared with only using global classification loss, concurrently considering local loss and the results of robust pose estimation enable the deep network to learn the representations of the body parts that prominently displayed in the image and gain the discriminative faculties on occluded scenes. Experimental results on multiple datasets, i.e., Market-1501, DukeMTMC, CUHK03, demonstrate the effectiveness of our method in a variety of scenarios. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

GradSA: Gradient Sparsification and Accumulation for Communication-Efficient Distributed Deep Learning 15th

GradSA: Gradient Sparsification and Accumulation for Communi...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Liu, Bo Jiang, Wenbin Zhao, Shaofeng Jin, Hai He, Bingsheng National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Huazhong University of Science and Technology Wuhan China Library Henan University of Economics and Law Zhengzhou China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9783030642426

Large-scale distributed deep learning is of great importance in various applications. For distributed training, the inter-node gradient communication often becomes the performance bottleneck. Gradient sparsification has been proposed to reduce the communication overhead. However, the sparsification only arbitrarily selects a small fraction of gradients, while the efficiency of selection dimension has been overlooked. Furthermore, gradient staleness is inevitable after applying the sparsification which will ultimately lead to model divergence. In this paper, we propose a staleness-compensated sparse stochastic gradient descent algorithm, GradSA, to improve the training efficiency. Layer-level gradients are sparsified to reduce the communication overhead, which conform to the characteristics of the network structure, and historical accumulation of the approximated gradients is utilized to speed up convergence. We demonstrate the model convergence acceleration and the efficiency of our layer-level selection over existing state-of-the-art works, such as DGC, TernGrad, and 8-Bit quantization. © 2020, Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Free Adversarial Training with Layerwise Heuristic Learning 11th

Free Adversarial Training with Layerwise Heuristic Learning

引用

11th International Conference on Image and Graphics, ICIG 2021

作者： Zhang, Haitao Shi, Yucheng Dong, Benyu Han, Yahong Li, Yuanzhang Kuang, Xiaohui College of Intelligence and Computing and Tianjin Key Lab of Machine Learning Tianjin University Tianjin China Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Information System Security Beijing China

ISBN: (纸本)9783030873578

Due to the existence of adversarial attacks, various applications that employ deep neural networks (DNNs) have been under threat. Adversarial training enhances robustness of DNN-based systems by augmenting training data with adversarial samples. Projected gradient descent adversarial training (PGD AT), one of the promising defense methods, can resist strong attacks. We propose "free" adversarial training with layerwise heuristic learning (LHFAT) to remedy these problems. To reduce heavy computation cost, we couple model parameter updating with projected gradient descent (PGD) adversarial example updating while retraining the same mini-batch of data, where we "free" and unburden extra updates. Learning rate reflects weight updating speed. Weight gradient indicates weight updating efficiency. If weights are frequently updated towards opposite directions in one training epoch, then there are redundant updates. For higher level of weight updating efficiency, we design a new learning scheme, layerwise heuristic learning, which accelerates training convergence by restraining redundant weight updating and boosting efficient weight updating of layers according to weight gradient information. We demonstrate that LHFAT yields better defense performance on CIFAR-10 with approximately 8% GPU training time of PGD AT and LHFAT is also validated on ImageNet. We have released the code for our proposed method LHFAT at https://***/anonymous530/LHFAT. © 2021, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Event Timeline Extraction Method Based on News Corpus 2

An Event Timeline Extraction Method Based on News Corpus

引用

2017 IEEE 2nd International Conference on Big Data Analysis（ICBDA 2017）

作者： Yaguang Wu Haichun Sun Chungang Yan Department of Computer Science and Technology Tongji University The Key Laboratory of Embedded System and Service Computing Tongji University College of Police Information Engineering People's Public Security University of China

ISBN: (纸本)9781509036202

Event extraction is an important research point in information extraction area, and news event extraction has a greater practical significance. The existing methods of extracting news event, which starts from the time element, is to identify the date sentences hold by Natural Language Processing and extract the event on the date by Text Clustering. However, they only process the news that holds a time-tag and gives up the news that has no accurate date, which easily leads an extraction deviation of significant events and reduces the accuracy of ordering the significant events. In this paper, improvement for this defect is to calculate the similarities between sentences to put part of the non-time-tag sentences into the right date container, thereby the accuracy of ordering the significant event is *** experiments and compared with the existing methods,the accuracy of ordering the significant events in this paper is improved by 14.6%.

关键词： event extraction text information mining sentence similarity timeline

来源：评论

学校读者我要写书评

暂无评论

A new method for image fusion based on fuzzy neural network

A new method for image fusion based on fuzzy neural network

引用

作者： Zhang, De-Gan Wang, Yuan-Yuan Liu, Wei-Wei Zhang, Xiao-Li Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of Technology 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology 300191 China

ISBN: (纸本)9780955529337

In pervasive computing paradigm, the image data obtained by a variety of multimedia, information equipment. In order to make use of these information reasonably and efficiently, a new method for image fusion based on fuzzy neural network has presented in this paper. It can fuse massive data from the multi-sensor image. Here, fuzzy neural network is a paraDel information processing model, there are more adaptive and self-organization, and can accomplish the complexity of real-time computing and mass data retrieval, it demonstrate its unique superiority of image understanding, pattern recognition and the handling of incomplete information. The fuzzy neural network system developed by us can be used in multi- sensor image fusion. Based on our experiments, it has been proved that the fusion is fast, effective, and can meet the real-time requirements of pervasive computing.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

A pervasive service discovery strategy based on peer to peer model

A pervasive service discovery strategy based on peer to peer...

引用

作者： Zhang, De-Gan Chen, Xu-Yan Li, Chao Li, Lin-Qing Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of Technology 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology 300191 China

ISBN: (纸本)9780955529337

In order to improve the efficiency of service discovery in the pervasive environment, this paper presents a new strategy of service discovery based on p2p network model. Reference the ring topology of chord algorithm and tbe algorithm used by DDT, tbe traditional single finger-table witch be maintained by each node in the ring will be changed into double finger-table: the Neigbbor-Finger-Table and Long-distance Finger-Table. The structure of the Neighbor-Finger-Table is the same as the traditional single finger-table's. The Long-distance Finger-Table can construct small-world network. Some similar algorithm uses random method to select remote access node, the new strategy is different from that, tbrough tbe calculation of the local node, it can ensure the scope of service can cover tbe entire network. The simulation shows the algorithm can effectively reduce the path length of service discovery, improve the service success rate, and control the path length of magnitude.

关键词： Small-world networks

来源：评论

学校读者我要写书评

暂无评论

GIRAFFE: A scalable distributed coordination service for large-scale systems 16

GIRAFFE: A scalable distributed coordination service for lar...

引用

16th IEEE International Conference on Cluster computing, CLUSTER 2014

作者： Shi, Xuanhua Lin, Haohong Jin, Hai Zhou, Bing Bing Yin, Zuoning Di, Sheng Wu, Song Services Computing Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology China Centre for Distributed and High Performance Computing School of Information Technologies University of Sydney Australia GraphSQL Inc. Australia INRIA Argonne National Laboratory United States

ISBN: (纸本)9781479955480

The scale of cloud services keeps increasing over time, significantly introducing huge challenges in system manageability and reliability. Designing coordination services in cloud is the right track to solve the above problems. However, existing coordination services (e.g., Chubby and ZooKeeper) only perform well in read-intensive scenario and small ensemble scales. To this end, we propose Giraffe, a scalable distributed coordination service. There are three important contributions in our design. (1) Giraffe organizes coordination servers using interior-node-disjoint trees for better scalability. (2) Giraffe employs a novel Paxos protocol for strong consistency and fault-tolerance. (3) Giraffe supports hierarchical data organization and in-memory storage for high throughput and low latency. We evaluate Giraffe on a high performance computing test-bed. The experimental results show that Giraffe gains much better write performance than ZooKeeper when server ensemble is large. Giraffe is nearly 300% faster than ZooKeeper on update operations when ensemble size is 50 servers. Experiments also show that Giraffe reacts and recovers more quickly than ZooKeeper against node failures. © 2014 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

CQ COMSOC: CALLING ALL COMSOC RADIO AMATEURS

引用

IEEE COMMUNICATIONS MAGAZINE 2015年第7期53卷 6-8页

作者： Benedetto, Sergio Zuckerman, Doug Mobility Services Laboratory Nissan Motor Co. Japan Guangdong Province Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences (CAS) China Graduate School of Media Design Keio University Japan Chinese Academy of Sciences (CAS) Shenzhen Institutes of Advanced Technology Shenzhen China

This month’s President’s Page is devoted to the initiatives and plans of the IEEE Communications Society (ComSoc) in the area of education and training. Enhancing the IEEE societies’ activities in the area of education and training is one of the strategic goals of IEEE, and it has been recognized as such also by ComSoc’s strategic and planning committee (see the January 2015 President’s Page). Education and training can be developed as the third pillar of ComSoc’s major technical activities and a revenue source to complement the two existing pillars: publications and conferences.

关键词： Green computing

来源：评论

学校读者我要写书评

暂无评论

Discrete Geometric Coded Data Layout for Large-scale Object Storage systems 21

Discrete Geometric Coded Data Layout for Large-scale Object ...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud computing, 16th IEEE International Conference on Social computing and Networking and 13th International Conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Tian, Yi Xu, Guangping Yang, Hongzhang Ni, Yue Cao, JiaXin Yang, Lei Tianjin University of Technology School of Computer Science and Engineering Tianjin China Novel Software Technology Tianjin Key Laboratory of Intelligence Computing Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China Information Technology Co. Ltd. China

ISBN: (纸本)9798350329223

Regenerating codes are new network codes proposed to reduce the data required for fault repair, which can improve the recovery efficiency of faulty nodes in data storage systems. However, unlike Reed-Solomon code, which repairs at the granularity of bytes, regenerating codes require data stored in large chunks but leads to severe read amplification, which reads out excess data when degraded read objects and increases degraded read time. That reflects a mutual constraint between improving recovery efficiency and degraded read performance, as manifested in the amplification of data reads, a vital issue considered in this *** solve this problem, we propose a new type of data layout - discrete geometric, which splits the object into a series of geometric sequences of data blocks. They are placed discretely into corresponding containers on the disks at different nodes, with containers of the same size made into a strip for encoding. The discrete characteristic ensures lower repair costs for degraded reads. The geometric characteristic ensures the repair performance of regenerating codes by large blocks, and read amplification can be mitigated through small blocks. To reduce IOPS for discrete geometric, we propose Discrete Geometric-Locally Regenerating Codes (DG-LRCs), guaranteeing lower degraded read latency while improving recovery *** results show that the degraded read time of DG-LRCs compared to regenerating codes combined with geometric partitioning is 22.56% lower at 2Gbpsand 60.56% lower at 4Gbps, and the recovery performance is 7.04 times better than that of RS code. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Design and realization of mobile government information services platform based on SMS

Design and realization of mobile government information serv...

引用

作者： Wang, Fayu Zhang, Hua Xu, Guangping Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Ministry of Education Tianjin University of Technology 300191 Tianjin China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology 300191 Tianjin China

ISBN: (纸本)9788988678251

As the development of mobile communication technology becomes gradual mature, the short message service which sends messages from the information platform to the mobile phone users has been a method for the most users to obtain information timely and conveniently. This thesis collates the short message service system exploited for the mobile phone users and the service platform for the network users to elaborate the function of the platform and the system structure of the short message platform briefly, and state the key technology of its design and operation minutely. The short message platform is consisted of a web server based on the database, a sending server and interface server. This platform employs three-level control tactics, the user, role and administrator to regulate the user's authority and guarantee the security of the system. So the system has a certain referent value for the design of such kind of short message platform.

关键词： Cellular telephones

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：