检索结果-内蒙古大学图书馆

A GPU-based parallel WFST decoder on nnet3

AIP Conference Proceedings 2019年第1期2073卷

作者： Yong Wang Jie Liu Chen Zhou Zhengbin Pang Shengguo Li Chunye Gong Xinbiao Gan Yurong Li 1Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha 410073 China

One performance-intensive part of automatic speech recognition is the weighted finite-state transducer (WFST) decoding. To solve the problem, we expand parallel Graphics processing Units (GPU) computing to the decoding period. We describe extension work based on Kaldi toolkit for speech recognition research. Our work can support weighted finite-state transducer decoding on Kaldi neural nets with CUDA toolkit. Our paper also expands an efficient parallel Viterbi beam decoding algorithm to decrease the speech recognition Real Time Factor (RTF) value. Together with our optimization algorithm, we have reached 2.3x speed up on the AISHELL corpus decoding. We also implement nnet3 decoder that improves real-time speed up with no word error rate raise.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RZKPB: A Privacy-Preserving Blockchain-Based Fair Transaction Method for Sharing Economy

RZKPB: A Privacy-Preserving Blockchain-Based Fair Transactio...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Bin Li Yijie Wang Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Hunan Changsha P.R. China

Emerging blockchain systems have been widely adopted in sharing economy, such as e-commerce, to allow mutually distrustful parties to transact fairly without trusted parties. Most blockchain systems, however, lack transactional privacy protection. All transactions, including trading relationship between pseudonyms and content transacted, are exposed on the blockchain. Although many existing privacy protection methods on the blockchain have been proposed, it is difficult to find a trade-off between keeping speed and protecting privacy of transactions. To address this limitation, we propose a novel privacy-preserving method RZKPB that does not store financial transactions in clear on the blockchain, thus retaining transactional privacy from the public's view. Meanwhile, these transactions are as proofs to solve disputes between trading partners. RZKPB ensures fairness and privacy of transactions between participants without adding a new trusted party and breaking the verifying protocol on the blockchain. We take the e-commerce as an example in sharing economy to introduce RZKPB in our paper. Our experimental results show that compared with existing privacy-preserving methods based on the blockchain, RZKPB is more efficient under different settings.

关键词： Privacy Protocols Encryption Distortion

来源：评论

学校读者我要写书评

暂无评论

Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions

Diagonalwise Refactorization: An Efficient Training Method f...

引用

International Joint Conference on Neural Networks

作者： Zheng Qin Zhaoning Zhang Dongsheng Li Yiming Zhang Yuxing Peng Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China

Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds. However, training depthwise convolution layers with GPUs is slow in current deep learning frameworks because their implementations cannot fully utilize the GPU capacity. To address this problem, in this paper we present an efficient method (called diagonalwise refactorization) for accelerating the training of depthwise convolution layers. Our key idea is to rearrange the weight vectors of a depthwise convolution into a large diagonal weight matrix so as to convert the depthwise convolution into one single standard convolution, which is well supported by the cuDNN library that is highly-optimized for GPU computations. We have implemented our training method in five popular deep learning frameworks. Evaluation results show that our proposed method gains 15.4× training speedup on Darknet, 8.4× on Caffe, 5.4× on PyTorch, 3.5× on MXNet, and 1.4× on TensorFlow, compared to their original implementations of depthwise convolutions.

关键词： Standards Graphics processing units Kernel Convolutional codes Training Acceleration Libraries

来源：评论

学校读者我要写书评

暂无评论

FPPB: A Fast and Privacy-Preserving Method Based on the Permissioned Blockchain for Fair Transactions in Sharing Economy

FPPB: A Fast and Privacy-Preserving Method Based on the Perm...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Bin Li Yijie Wang Peichang Shi Huan Chen Li Cheng Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha Hunan P.R. China

Blockchain is a distributed system with efficient transaction recording and has been widely adopted in sharing economy. Although many existing privacy-preserving methods on the blockchain have been proposed, finding a trade-off between keeping speed and preserving privacy of transactions remain challenging. To address this limitation, we propose a novel Fast and Privacy-preserving method based on the Permissioned Blockchain (FPPB) for fair transactions in sharing economy. Without breaking the verifying protocol and bringing additional off-blockchain interactive communication, FPPB protects the privacy and fairness of transactions. Additionally, experiments are implemented in EthereumJ (a Java implementation of the Ethereum protocol) to measure the performance of FPPB. Compared with normal transactions without cryptographic primitives, FPPB only slows down transactions slightly.

关键词： Privacy Cloud computing Encryption Registers Protocols

来源：评论

学校读者我要写书评

暂无评论

Diagonalwise refactorization: An efficient training method for depthwise convolutions

arXiv

引用

arXiv 2018年

作者： Qin, Zheng Zhang, Zhaoning Li, Dongsheng Zhang, Yiming Peng, Yuxing Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

TEMPORAL PYRAMID RELATION NETWORK FOR VIDEO-BASED GESTURE RECOGNITION

TEMPORAL PYRAMID RELATION NETWORK FOR VIDEO-BASED GESTURE RE...

引用

IEEE International Conference on Image processing

作者： Ke Yang Rongchun Li Peng Qiao Qiang Wang Dongsheng Li Yong Dou National Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China

Gesture recognition in video is an important application of computer vision. However, there are few works talked about the temporal order or relation of the frames in video, which is important for model gestures. In this paper, we propose Temporal Pyramid Relation Network (TPRN) which can model the temporal relation of video frames effectively and efficiently. First, we use Temporal Pyramid Pooling (TPP) layer to get temporal feature sequences of multiple scale pyramids. Then, a Temporal Relation Network (TRN) is stacked on the feature sequence of each scale respectively to model the temporal relations of video frames at multiple scales. At last, representations of all scales are aggregated to get the final prediction. TPRN can take video clips of various length as input and is scalable for video length. We evaluate TPRN on a recently released very large video-based gesture recognition dataset - 20BN-Jester dataset v1, and TPRN achieves competitive performance.

关键词： Feature extraction Gesture recognition Solid modeling Hidden Markov models Three-dimensional displays Computational modeling Training

来源：评论

学校读者我要写书评

暂无评论

Merging and evolution: Improving convolutional neural networks for mobile applications

arXiv

引用

arXiv 2018年

作者： Qin, Zheng Zhang, Zhaoning Zhang, Shiqing Yu, Hao Peng, Yuxing Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China

Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard "fully-connected" convolutions, these convolutions are more computationally economical. However, "sparsely-connected" convolutions block the inter-group information exchange, which induces severe performance degradation. To address this issue, we present two novel operations named merging and evolution to leverage the inter-group information. Our key idea is encoding the inter-group information with a narrow feature map, then combining the generated features with the original network for better representation. Taking advantage of the proposed operations, we then introduce the Merging-and-Evolution (ME) module, an architectural unit specifically designed for compact networks. Finally, we propose a family of compact neural networks called MENet based on ME modules. Extensive experiments on ILSVRC 2012 dataset and PASCAL VOC 2007 dataset demonstrate that MENet consistently outperforms other state-of-the-art compact networks under different computational budgets. For instance, under the computational budget of 140 MFLOPs, MENet surpasses ShuffleNet by 1% and MobileNet by 1.95% on ILSVRC 2012 top-1 accuracy, while by 2.3% and 4.1% on PASCAL VOC 2007 mAP, respectively. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

FD-Mobilenet: Improved mobilenet with a fast downsampling strategy

arXiv

引用

arXiv 2018年

作者： Qin, Zheng Zhang, Zhaoning Chen, Xiaotao Peng, Yuxing Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China

We present Fast-Downsampling MobileNet (FD-MobileNet), an efficient and accurate network for very limited computational budgets (e.g., 10-140 MFLOPs). Our key idea is applying a fast downsampling strategy to MobileNet framework. In FD-MobileNet, we perform 32× downsampling within 12 layers, only half the layers in the original MobileNet. This design brings three advantages: (i) It remarkably reduces the computational cost. (ii) It increases the information capacity and achieves significant performance improvements. (iii) It is engineering-friendly and provides fast actual inference speed. Experiments on ILSVRC 2012 and PASCAL VOC 2007 datasets demonstrate that FD-MobileNet consistently outperforms MobileNet and achieves comparable results with ShuffleNet under different computational budgets, for instance, surpassing MobileNet by 5.5% on the ILSVRC 2012 top-1 accuracy and 3.6% on the VOC 2007 mAP under a complexity of 12 MFLOPs. On an ARM-based device, FD-MobileNet achieves 1.11× inference speedup over MobileNet and 1.82× over ShuffleNet under the same complexity. Copyright © 2018, The Authors. All rights reserved.

关键词： Signal sampling

来源：评论

学校读者我要写书评

暂无评论

Multi-Owner Keyword Search over Shared Data without Secure Channels in the Cloud

引用

China Communications 2017年第5期14卷 124-133页

作者： Yilun Wu Xicheng Lu Jinshu Su Peixin Chen Xiaofeng Wang Bofeng Zhang College of Computer National University of Defense TechnologyChangsha 410073China National Laboratory for Parallel and Distributed Processing National University of Defense TechnologyCbangsba 410073China

Searchable encryption allows cloud users to outsource the massive encrypted data to the remote cloud and to search over the data without revealing the sensitive information. Many schemes have been proposed to support the keyword search in a public cloud. However,they have some potential limitations. First,most of the existing schemes only consider the scenario with the single data owner. Second,they need secure channels to guarantee the secure transmission of secret keys from the data owner to data users. Third,in some schemes,the data owner should be online to help data users when data users intend to perform the search,which is *** this paper,we propose a novel searchable scheme which supports the multi-owner keyword search without secure channels. More than that,our scheme is a non-interactive solution,in which all the users only need to communicate with the cloud server. Furthermore,the analysis proves that our scheme can guarantee the security even without secure channels. Unlike most existing public key encryption based searchable schemes,we evaluate the performance of our scheme,which shows that our scheme is practical.

关键词： keyword search cloud security secure channels proxy re-encryption

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Cooperative Trail Following for Multi-Robot System

Deep Learning-based Cooperative Trail Following for Multi-Ro...

引用

International Joint Conference on Neural Networks

作者： Mingyang Geng Yiying Li Bo Ding Huaimin Wang National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology ChangSha China

Following trails in the wild is an essential capability of out-door autonomous mobile robots. Recently, deep learning-based approaches have made great advancements in this field. However, the existing research only focuses on the trail following with a single robot. In contrast, many robotic tasks in the reality, such as search and patrolling, are conducted by a group of robots. While these robots are grouped to move in the wild, they can cooperate to significantly promote the trail following accuracy, for example, by sharing images of different view angles or real-time decision fusion. This paper proposes such an approach named DL-Cooper that enables multi-robot vision-based trail following based on deep learning algorithms. It allows each robot to make a decision respectively with deep neural network and then fusion the decisions on the collective level with the support of back-end cloud computing infrastructure. It also takes Quality of Service (QoS) assurance, a very essential property of robotic software, into consideration. By limiting the condition to fusion decisions, the time latency can be minimally sacrificed. Experiments on the real-world dataset show that our approach has significantly improved the accuracy of the single-robot system.

关键词： Task analysis Robot kinematics Machine learning Multi-robot systems Quality of service Cloud computing

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：