检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Yu, Hao Zhang, Zhaoning Qin, Zheng Wu, Hao Li, Dongsheng Zhao, Jun Lu, Xicheng Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China College of Electronic and Engineering National University of Defense Technology Changsha China College of Meteorology and Oceanology National University of Defense Technology Changsha China

Modern object detectors usually suffer from low accuracy issues, as foregrounds always drown in tons of backgrounds and become hard examples during training. Compared with those proposal-based ones, real-time detectors are in far more serious trouble since they renounce the use of regionproposing stage which is used to filter a majority of backgrounds for achieving real-time rates. Though foregrounds as hard examples are in urgent need of being mined from tons of backgrounds, a considerable number of state-of-the-art realtime detectors, like YOLO series, have yet to profit from existing hard example mining methods, as using these methods need detectors fit series of prerequisites. In this paper, we propose a general hard example mining method named Loss Rank Mining (LRM) to fill the gap. LRM is a general method for real-time detectors, as it utilizes the final feature map which exists in all real-time detectors to mine hard examples. By using LRM, some elements representing easy examples in final feature map are filtered and detectors are forced to concentrate on hard examples during training. Extensive experiments validate the effectiveness of our method. With our method, the improvements of YOLOv2 detector on auto-driving related dataset KITTI and more general dataset PASCAL VOC are over 5% and 2% mAP, respectively. In addition, LRM is the first hard example mining strategy which could fit YOLOv2 perfectly and make it better applied in series of real scenarios where both real-time rates and accurate detection are strongly demanded. Copyright © 2018, The Authors. All rights reserved.

关键词： Mining

来源：评论

学校读者我要写书评

暂无评论

Loss Rank Mining: A General Hard Example Mining Method for Real-time Detectors

Loss Rank Mining: A General Hard Example Mining Method for R...

引用

International Joint Conference on Neural Networks

作者： Hao Yu Zhaoning Zhang Zheng Qin Hao Wu Dongsheng Li Jun Zhao Xicheng Lu Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China College of Electronic and Engineering National University of Defense Technology Changsha China College of Meteorology and Oceanology National University of Defense Technology Changsha China

Modern object detectors usually suffer from low accuracy issues, as foregrounds always drown in tons of back-grounds and become hard examples during training. Compared with those proposal-based ones, real-time detectors are in far more serious trouble since they renounce the use of region-proposing stage which is used to filter a majority of back-grounds for achieving real-time rates. Though foregrounds as hard examples are in urgent need of being mined from tons of backgrounds, a considerable number of state-of-the-art real-time detectors, like YOLO series, have yet to profit from existing hard example mining methods, as using these methods need detectors fit series of prerequisites. In this paper, we propose a general hard example mining method named Loss Rank Mining (LRM) to fill the gap. LRM is a general method for real-time detectors, as it utilizes the final feature map which exists in all real-time detectors to mine hard examples. By using LRM, some elements representing easy examples in final feature map are filtered and detectors are forced to concentrate on hard examples during training. Extensive experiments validate the effectiveness of our method. With our method, the improvements of YOLOv2 detector on auto-driving related dataset KITTI and more general dataset PASCAL VOC are over 5% and 2% mAP, respectively. In addition, LRM is the first hard example mining strategy which could fit YOLOv2 perfectly and make it better applied in series of real scenarios where both real-time rates and accurate detection are strongly demanded.

关键词： Detectors Real-time systems Feature extraction Training Object detection Pipelines Task analysis

来源：评论

学校读者我要写书评

暂无评论

CloudDPI: Cloud-based privacy-preserving deep packet inspection via reversible sketch 1

引用

9th International Symposium on Cyberspace Safety and Security, CSS 2017

作者： Li, Jie Su, Jinshu Wang, Xiaofeng Sun, Hao Chen, Shuhui School of Computer National University of Defense Technology Changsha Hunan410073 China National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha Hunan410073 China

ISBN: (数字)9783319694719

ISBN: (纸本)9783319694702

Hardware-based middleboxes are ubiquitous in computer networks, which usually incur high deployment and management expenses. A recently arsing trend aims to address those problems by outsourcing the functions of traditional hardware-based middleboxes to high volume servers in a cloud. This technology is promising but still faces a few challenges. First, the widely adopted data encryption techniques contradict with payload inspection needs of some middleboxes such as DPI and IDS devices. Second, the inspection rules of middleboxes may be commercial properties, thus the middlebox providers want to keep their rules confidential under third-party cloud environments, and this creates hindrances for the cloud to perform outsourced middlebox functions. Third, performance of the outsourced middlebox is an inevitable issue that needs deliberate consideration. In this paper, we propose a cloud-based DPI middlebox implementation which performs payload inspection over encrypted traffic while preserving the privacy of both communication data and inspection rules. Our design employs a modified reversible sketch structure which is used for efficient error-free membership testing, and we utilize unkeyed one-way hash functions instead of complex cryptographic protocols to achieve the privacy preservation requirements. CloudDPI supports a wide range of real-world inspection rules, we conduct evaluations on ClamAV rule set and the experiment results demonstrate the effectiveness of our proposal. © 2017, Springer International Publishing AG.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Fine-grained checkpoint based on non-volatile memory

引用

Frontiers of Information technology & Electronic Engineering 2017年第2期18卷 220-234页

作者： Wen-zhe ZHANG Kai LU Mikel LUJAN Xiao-ping WANG Xu ZHOU Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha 410072 China School of Computer The University of Manchester Manchester M13 9PL UK

New non-volatile memory （e.g., phase-change memory） provides fast access, large capacity, byteaddressability, and non-volatility features. These features, fast-byte-persistency, will bring new opportunities to fault tolerance. We propose a fine-grained checkpoint based on non-volatile memory. We extend the current virtual memory manager to manage non-volatile memory, and design a persistent heap with support for fast allocation and checkpointing of persistent objects. To achieve a fine-grained checkpoint, we scatter objects across virtual pages and rely on hardware page-protection to monitor the modifications. In our system, two objects in different virtual pages may reside on the same physical page. Modifying one object would not interfere with the other object. This allows us to monitor and checkpoint objects smaller than 4096 bytes in a fine-grained way. Compared with previous page-grained based checkpoint mechanisms, our new checkpoint method can greatly reduce the data copied at checkpoint time and better leverage the limited bandwidth of non-volatile memory.

关键词： Non-volatile memory Byte-persistency Persistent heap Fine-grained checkpoint

来源：评论

学校读者我要写书评

暂无评论

Growing construction and adaptive evolution of complex software systems

引用

science China(Information sciences) 2016年第5期59卷 5-7页

作者： Huaimin WANG Bo DING National Key Laboratory of Parallel and Distributed Processing College of ComputerNational University of Defense Technology

distributed software systems are becoming more and more complex *** is easy to find a huge amount of computing nodes in a nationwide or global information *** example,We Chat(Wei Xin),a well-known mobile application in China,has reached a record of 650 million monthly active users in the third quarter of *** the same time,researchers are starting to talk about software systems which have billions of lines of codes[1]or can last one hundred years.

关键词： Growing construction and adaptive evolution of complex software systems

来源：评论

学校读者我要写书评

暂无评论

parallel Algorithm Design for Audio Feature Extraction

Parallel Algorithm Design for Audio Feature Extraction

引用

2017 5th International Conference on Machinery,Materials and Computing technology(ICMMCT 2017)

作者： Xiaocheng Luo Jingfei Jiang Junjie Zhu Yong Dou National Laboratory for Parallel and Distributed Processing National University of Defense Technology

Audio feature extraction is a very important technique in the field of sound processing. It extremely impacts the effectiveness and correctness of sound recognition, sound verification, etc. It is a computation intensive stage in the whole sound recognition process, which is a challenging for acceleration. In this paper, a coarse-grained parallel feature extraction algorithm for high throughput of audio slices is proposed to improve the efficiency of audio feature extraction. Three typical audio feature extraction algorithms, Mel Frequency Cepstrum Coefficients(MFCC), Spectrogram image features(SIF), Octave-Based Spectral Contrast, are chosen to parallelize. Experiments results on different platforms show that the speedup of accelerated audio feature extraction is up to 17.23 on the platform with 16 cores 32 threads.

关键词： Feature Extraction Sound Recognition parallel Algorithm

来源：评论

学校读者我要写书评

暂无评论

Zero Pronoun Identification in Chinese Language with Deep Neural Networks

Zero Pronoun Identification in Chinese Language with Deep Ne...

引用

2017 2nd International Conference on Control, Automation and Artificial Intelligence(CAAI2017)

作者： Tao Chang Shaohe Lv Xiaodong Wang Dong Wang National Laboratory for Parallel and Distributed Processing National University of Defense Technology

ISBN: (纸本)9781510845541

Zero pronoun resolution is very important in natural language processing. Identification of zero pronoun is the fundamental task of its resolution. Existing feature engineering based identification approaches are unsuitable for big data applications due to labor-intensive work. Furthermore, as extracted from parse trees which are not unique for a certain sentence, features may be improper for zero pronoun identification. In this paper, we constructed a two-layer stacked bidirectional LSTM model to tackle identification of zero pronoun. To extract semantic knowledge, the first layer obtains the structure information of the sentence, and the second layer combines the part-of-speech information with obtained structure information. The results in two different kinds of experimental environment show that, our approach significantly outperforms the state-of-the-art method with an absolute improvement of 4.3% and 20.3% F-score in Onto Notes 5.0 corpus respectively.

关键词： zero pronoun Identification LSTM

来源：评论

学校读者我要写书评

暂无评论

A Research on Minisat Using Coarse-grained parallel Technique Based on Multi-core and Multi-platform

A Research on Minisat Using Coarse-grained Parallel Techniqu...

引用

2017 5th International Conference on Machinery,Materials and Computing technology(ICMMCT 2017)

作者： Junjie Zhu Jingfei Jiang Xiaocheng Luo Yong Dou National Laboratory of Parallel and Distributed Processing National University of Defence Technology

In this paper, we make a research on a widely-used SAT solver, Minisat, aiming to improve its performance using coarse-grained parallel method on multi-core and multi-platform. Firstly, we parallel the Minisat by mean of Open MP and test its performance with different threads by running a test set consisting of 2000 SAT problems on an X86 computer. Besides, a scheduling strategy with time sequence is added to the process and achieves a better speed-up ratio. Then, we move the algorithm to an ARM computer and repeat the same process, finding that the performance of Minisat on X86 is better than that on ARM, but ARM platform has a better scale effect than X86 platform when running at full load and is able to perform better than X86 when they have the same hardware configuration.

关键词： Minisat solver coarse-grained multi-core multi-platform

来源：评论

学校读者我要写书评

暂无评论

General audio tagging with ensembling convolutional neural networks and statistical features

arXiv

引用

arXiv 2018年

作者： Xu, Kele Zhu, Boqing Kong, Qiuqiang Mi, Haibo Ding, Bo Wang, Dezhi Wang, Huaimin National Key Laboratory of Parallel and Distributed Processing Changsha China College of Computer National University of Defense Technology Changsha China University of Surrey United Kingdom College of Meteorology and Oceanography National Univ. of Defense Tech Changsha China

Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general audio tagging challenge. The contributions of our solution include: We investigated a variety of convolutional neural network architectures to solve the audio tagging task. Statistical features are applied to capture statistical patterns of audio features to improve the classification performance. Ensemble learning is applied to ensemble the outputs from the deep classifiers to utilize complementary information. a sample reweight strategy is employed for ensemble training to address the noisy label problem. Our system achieves a mean average precision (mAP@3) of 0.958, outperforming the baseline system of 0.704. Our system ranked the 1st and 4th out of 558 submissions in the public and private leaderboard of DCASE 2018 Task 2 challenge. Copyright © 2018, 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

Efficient detection of dangling pointer error for C/C++ programs 2

Efficient detection of dangling pointer error for C/C++ prog...

引用

2nd Annual International Conference on Information System and Artificial Intelligence, ISAI 2017

作者： Zhang, Wenzhe Science and Technology on Parallel and Distributed Laboratory State Key Laboratory of High Performance Computing State Key Laboratory of High-end Server and Storage Technology College of Computer National University of Defense Technology Changsha China

Dangling pointer error is pervasive in C/C++ programs and it is very hard to detect. This paper introduces an efficient detector to detect dangling pointer error in C/C++ programs. By selectively leave some memory accesses unmonitored, our method could reduce the memory monitoring overhead and thus achieves better performance over previous methods. Experiments show that our method could achieve an average speed up of 9% over previous compiler instrumentation based method and more than 50% over previous page protection based method. © Published under licence by IOP Publishing Ltd.

关键词： Errors

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：