检索结果-内蒙古大学图书馆

distributed sparse bundle adjustment algorithm based on three-dimensional point partition and asynchronous communication

引用

Frontiers of Information technology & Electronic Engineering 2018年第7期19卷 889-904页

作者： Xiao-long SHEN Yong DOU Steven MILLS David M EYERS Huan FENG Zhiyi HUANG College of Computer National University of Defense Technology Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Department of Computer Science University of Otago Department of Computer Science Tsinghua University

Sparse bundle adjustment(SBA) is a key but time-and memory-consuming step in three-dimensional(3 D) reconstruction. In this paper, we propose a 3 D point-based distributed SBA algorithm(DSBA) to improve the speed and scalability of SBA. The algorithm uses an asynchronously distributed sparse bundle adjustment(A-DSBA)to overlap data communication with equation computation. Compared with the synchronous DSBA mechanism(SDSBA), A-DSBA reduces the running time by 46%. The experimental results on several 3 D reconstruction datasets reveal that our distributed algorithm running on eight nodes is up to five times faster than that of the stand-alone parallel SBA. Furthermore, the speedup of the proposed algorithm(running on eight nodes with 48 cores) is up to41 times that of the serial SBA(running on a single node).

关键词： Sparse bundle adjustment parallel distributed sparse bundle adjustment Three-dimensional reconstruction Asynchronous

来源：评论

学校读者我要写书评

暂无评论

Aircraft Segmentation Based On Deep Learning framework : from extreme points to remote sensing image segmentation

Aircraft Segmentation Based On Deep Learning framework : fro...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Lei Zhao Peng Qiao Yong Dou Science and Technology on Parallel and Distributed Laboratory National University of Defense Changsha China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

Remote sensing image segmentation is a very important technology. Although the segmentation method based on convolutional neural networks (CNNs) has achieved promising results in natural image test set, e.g. VOC or COCO, they provide inferior performance when being transferred to remote sensing images. Due to the limits of labeled remote sensing images, finetuning pre-trained CNNs using remote sensing images do not benefit the image segmentation performance. Inspired by the recent works of interactive segmentation methods which exploit several extreme clicks that are fed into CNNs to improve the accuracy of the segmentation, we propose an effective method to improve the segmentation accuracy, which uses four extreme points (the top, bottom, left, and right) as the guide information. In terms of mIoU, our method achieves 84.4% on remote sensing image dataset, which outperforms the previous work by 23.1%. Compared with the previous interactive segmentation methods, the proposed method achieves superior performance. In addition, an improved method with an extra point is proposed based on the inaccurate part of results obtained by four extreme points. It is very feasible to be applied in an interactive segmentation toolbox.

关键词： Image segmentation Remote sensing Training Aircraft Perturbation methods Semantics Heating systems

来源：评论

学校读者我要写书评

暂无评论

An Effective Design to Improve the Efficiency of DPUs on FPGA

An Effective Design to Improve the Efficiency of DPUs on FPG...

引用

International Conference on parallel and distributed Systems (ICPADS)

作者： Yutian Lei Qingyong Deng Saiqin Long Shaohui Liu Sangyoon Oh The Key Laboratory of Hunan Province for Internet of Things and Information Security The School of Computer Science Science and Technology on Parallel and Distributed Processing Laboratory Xiangtan University Xiangtan China The Artificial Intelligence Center PengCheng Laboratory shenzhen China Ajou University Suwon-si Republic of Korea

The following topics are dealt with: cloud computing; learning (artificial intelligence); resource allocation; security of data; mobile computing; neural nets; optimisation; parallel processing; scheduling; and storag... 详细信息

ISBN: (数字)9781728190747

ISBN: (纸本)9781728183824

关键词： Deep learning Schedules Multicore processing Logic gates Throughput Acceleration Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Audio Tagging by Cross Filtering Noisy Labels

arXiv

引用

arXiv 2020年

作者： Zhu, Boqing Xu, Kele Kong, Qiuqiang Wang, Huaimin Peng, Yuxing Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha410073 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

—High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our framework for providing more complementary information of the audio. Then, though the cooperation and interaction of two neural networks, we divide the dataset into curated and noisy subsets by incrementally pick out the possibly correctly labeled data from the noisy data. Moreover, our approach leverages the multitask learning on curated and noisy subsets with different loss function to fully utilize the entire dataset. The noisy-robust loss function is employed to alleviate the adverse effects of incorrect labels. On both the audio tagging datasets FSDKaggle2018 and FSDKaggle2019, empirical results demonstrate the performance improvement compared with other competing approaches. On FSDKaggle2018 dataset, our method achieves state-of-the-art performance and even surpasses the ensemble models. Copyright © 2020, 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

Fast Nonlocal Diffusion by Stacking Local Filters for Image Denoising

Fast Nonlocal Diffusion by Stacking Local Filters for Image ...

引用

2019国际计算机前沿大会

作者： Peng Qiao Weichu Sun Yong Dou Rongchun Li Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology University of South China

Many image denoising methods achieve state-of-the-art performance with little consideration of computation efficiency. With the popularity of high-definition imaging devices, these denoising methods do not scale well to the high-definition images. Therefore, a fast image denoising method is proposed to meet the demand of processing highdefinition images. Based on the analysis of the distribution of the distance distrs between the similar patches and their reference patches from a semantic aspect, the large distrss was found to occur while their contribution to the overall distribution was small. Therefore, the nonlocal filters was replaced in trainable non-local reaction diffusion(TNLRD)with local filters. For image with 4096 × 4096 resolution, the proposed method runs about 6 times faster than TNLRD via a single-thread CPU implementation. And the GPU implementation of the proposed method is about 10 times faster than the CPU implementation. Furthermore,the proposed model achieves competing denoising performance compared with TNLRD in terms of PSNR and SSIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on accelerating CEE-DGCNN event extraction algorithm based on multi-CPU platform

引用

Journal of Physics: Conference Series 2021年第1期1738卷

作者： Yan Li Jinfei Jiang Jinwei Xu Zikai Gao Yong Dou Haifang Zhou Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha 410005 China Department of Computational Science National University of Defense Technology Changsha 410005 China

With the development of the Internet, the volume of information is expanding rapidly, and the complex information makes it particularly important to extract information quickly and intelligently. Event extraction algorithm is such a kind of fast and accurate information acquisition algorithm. With the development of deep learning in recent years, deep learning also shines in the field of time extraction. CEE-DGCNN network is an efficient and accurate event extraction algorithm for Chinese text. At present, the acceleration research on deep learning in the academic community mainly focuses on GPU, FPGA and other platforms. In fact, compared with these platforms, CPU is more versatile. Considering that the algorithm should have universality and universality in industrial application, this paper makes an in-depth analysis of CEE-DGCNN algorithm to study its acceleration on CPU. Experiments were carried out on x86 and ARM architectures respectively, and good acceleration effects were achieved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improve the Detection of Clustered Outliers via Outlier Score Propagation

Improve the Detection of Clustered Outliers via Outlier Scor...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yongmou Li Yijie Wang Hongtao Guan Science and Technology on Parallel and Distributed Laboratory College of Computer National University of Defense Technology Changsha China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Most of the existing outlier detection methods in the literature often adopt the assumption that the outliers would locate in the low-density area of the input data space. However, such low-density assumption may not hold in the presence of clustered outliers, which usually demonstrate relatively high density. For this reason, the clustered and cluster-based outlier detection methods are proposed; however, these methods either make strong data distribution assumptions or rely on the high-quality clustering results which are often not available. To address this issue, we propose a graph-based outlier detection approach which is capable of significantly enhancing the performance of existing outlier detection methods, in the presence of clustered outliers. Experiments are conducted on both synthesized and real-world datasets to demonstrate the superiority of our proposed method. In particular, our proposed method outperforms the state-of-the-art clustered outlier detection methods by a large margin.

关键词： Anomaly detection Support vector machines Kernel distributed databases Forestry Vegetation Transforms

来源：评论

学校读者我要写书评

暂无评论

A control system architecture with cloud platform for multi-UAV surveillance 4

A control system architecture with cloud platform for multi-...

引用

4th IEEE SmartWorld, 15th IEEE International Conference on Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP/SCI 2018

作者： Hong, Chen Shi, Dianxi Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9781538693803

Unmanned aerial vehicle is considered one of the most promising technologies. In the multi-UAV systems, a great challenge is to control multiple UAVs remotely by one person without being limited by distance. In this paper, to address this problem, we propose a control system architecture based on cloud platform which has been developed in order to allow multiple users to control and monitor multiple UAVs simultaneously irrespective of the location. Besides, the cloud platform acts as a remote brain for UAVs by providing extra storage and computing resources. This system architecture not only simplifies the development of control station, but also enhances the capabilities of unmanned system. © 2018 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

parallel computing for large-scale author name disambiguation in medline 21

Parallel computing for large-scale author name disambiguatio...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data science and Systems, HPCC/SmartCity/DSS 2019

作者： Tang, Anyao Wu, Chengkun Liu, Jie Wang, Wei Yang, Xi Xing, Yuting Science and Technology on Parallel and Distributed Processing Laboratory Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha410073 China State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha410073 China College of Computer National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9781728120584

Author name disambiguation (AND) is an important task in the field of scientific data mining. It has become a great challenge with the rapid growth of academic digital libraries. The task of AND for a large number of authors is computationally intensive. In particular, an author's name in MEDLINE is represented by full last name and initials, like 'Zhang S', which leads to a lot of identical strings that actually represent different names. In this paper, we proposed an efficient algorithm for parallel AND computation. The proposed algorithm mainly addresses the load balancing issue across many computing nodes. It involves the following strategies:(1) Author-based load balancing, which splits the computation load for each core by author name labels. (2) Matrix-based strategy, which calculates the pairwise similarity between publications and saves them in a matrix globally shared by all processes. Then group them by width-first search. We combine the above two strategies, the second of which is used to calculate authors with a large number of documents, and the other authors apply the first. We constructed a publications database written by Chinese authors from MEDLINE, the biggest public database for biomedical literature (abstracts). For benchmark testing, we experimented our algorithm with a dataset of 1 million publications on the Tianhe-2A supercomputer. Firstly, we trained an AND classifier that can achieve 98.1% of F1. The serial computation time is estimated to be approximately 246 hours, while the parallel execution time is approximately 66 hours in the case of four cores on a single node (with a speedup of 3.7x). Finally, we reduced the total parallel computing time of 1 million documents to about 2 hours and achieved 65.8% of parallelism efficiency using 200 cores on 90 nodes. © 2019 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

A distributed Computing Framework Based on Variance Reduction Method to Accelerate Training Machine Learning Models

A Distributed Computing Framework Based on Variance Reductio...

引用

IEEE International Conference on Joint Cloud Computing (JCC)

作者： Zhen Huang Mingxing Tang Feng Liu Jinyan Qiu Hangjun Zhou Yuan Yuan Changjian Wang Dongsheng Li Yuxing Peng Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China H.R. Support Center PLA Changsha China Hunan University of Finance and Economics Changsha China

ISBN: (数字)9781728169811

ISBN: (纸本)9781728169828

To support large-scale intelligent applications, distributed machine learning based on JointCloud is an intuitive solution scheme. However, the distributed machine learning is difficult to train due to that the corresponding optimization solver algorithms converge slowly, which highly demand on computing and memory resources. To overcome the challenges, we propose a computing framework for L-BFGS optimization algorithm based on variance reduction method, which can utilize a fixed big learning rate to linearly accelerate the convergence speed. To validate our claims, we have conducted several experiments on multiple classical datasets. Experimental results show that the computing framework accelerate the training process of solver and obtain accurate results for machine learning algorithms.

关键词： Acceleration Stochastic processes Machine learning algorithms Approximation algorithms Symmetric matrices Machine learning Computational modeling

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：