检索结果-内蒙古大学图书馆

2021年第二届控制、机器人和智能系统国际会议

作者： Wanrong Huang Yaqing Hu Shuofeng Hu Jingde Liu State Key Laboratory of High Performance Computing National University of Defense Technology Center for Computational Biology Beijing Institute of Basic Medical Sciences College of Joint Operation National Defense University

Deep neural networks have achieved remarkable results in largescale data ***,they have not performed well on few-shot image classification *** we propose a new metalearning approach composed of an embedding network and a linear classifier *** the training phase,our approach(called Transformation Network) learns to learn a classifier by transforming the feature vectors produced by the embedding *** trained,a Transformation Network is able to classify images of new classes by the learned *** ability of learning a discriminatively trained classifier could make our architecture adapt fast to new examples from unseen *** further describe implementation details upon the architecture convolutional networks and linear transformation *** demonstrate that our approach achieves improved performance on few-shot image classification tasks on two benchmarks and a self-made dataset.

关键词： few-shot learning meta-learning embedding classifier learner deep learning

来源：评论

学校读者我要写书评

暂无评论

Explicitly represent the boundary of ReLU NN as a classifier and measure its robustness

Explicitly represent the boundary of ReLU NN as a classifier...

引用

International Conference on Electronics, Communications and Information technology (CECIT)

作者： Yangyi Hu College of Computer Science and Technology Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China College of Computer Science National University of Defense Technology Changsha China

ISBN: (纸本)9781665437585

Adversarial examples pose a great threat to the application of neural network as a classifier in areas with high security requirements. Intuitively, the adversarial property of neural network is closely related to the boundary. However, works barely give a rigorous description of it. This paper for the first time studies the boundary of ReLU NN, which separates the sample space into distinct cells, each of which belongs to the same class. During the demonstration, we discuss the algebraic property of border points upon the separating boundary and the topological difference between border points and odd ones. We derive Theorem III.7 to give a rigorous, comprehensive and concise description on the boundary of ReLU NN. Furthermore, an algorithm, based on the description, is proposed to give a standard and exact metric for the local robustness of ReLU NN. This metric gives the local adversarial property of NN and reflects some aspects of its security performance, i.e. the nimimum distortion needed to craft an adversarial example. To the best of our knowledge, this is the first work proposed to give a rigorous and example-specific metric for the local robustness of ReLU NN.

关键词： Measurement Artificial neural networks Programming Distortion Robustness Time measurement Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

Soccer match broadcast video analysis method based on detection and tracking

Soccer match broadcast video analysis method based on detect...

引用

作者： Li, Hongyu Yang, Meng Yang, Chao Kang, Jianglang Suo, Xiang Meng, Weiliang Li, Zhen Mao, Lijuan Sheng, Bin Qi, Jun School of Information science and Technology Beijing Forestry University Beijing China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration Beijing China School of Athletic Performance Shanghai University of Sport Shanghai China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong Univerity Shanghai China Department of Computing Xi'an JiaoTong-Liverpool University Suzhou China

We propose a comprehensive soccer match video analysis pipeline tailored for broadcast footage, which encompasses three pivotal stages: soccer field localization, player tracking, and soccer ball detection. Firstly, we introduce sports camera calibration to seamlessly map soccer field images from match videos onto a standardized two-dimensional soccer field template. This addresses the challenge of consistent analysis across video frames amid continuous camera angle changes. Secondly, given challenges such as occlusions, high-speed movements, and dynamic camera perspectives, obtaining accurate position data for players and the soccer ball is non-trivial. To mitigate this, we curate a large-scale, high-precision soccer ball detection dataset and devise a robust detection model, which achieved the (Formula presented.) of 80.9%. Additionally, we develop a high-speed, efficient, and lightweight tracking model to ensure precise player tracking. Through the integration of these modules, our pipeline focuses on real-time analysis of the current camera lens content during matches, facilitating rapid and accurate computation and analysis while offering intuitive visualizations. © 2024 John Wiley & Sons Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Study on the Effect of Acid Rain Erosion on the Adhesion Properties of Asphalt-Aggregate Interface

SSRN

引用

SSRN 2024年

作者： Meng, Yongjun Tan, Shuang Mo, Shuyi Lai, Jun Yao, Qilian Rong, Hongliu Chen, Jinping Meng, Fujia College of Civil Engineering and Architecture Guangxi University Guangxi Nanning530004 China Key Laboratory of Disaster Prevention and Engineering Safety of Ministry of Education Guangxi Nanning530004 China Special Geological Highway Safety Engineering Technology Research Center of Guangxi Nanning530004 China National High- performance Computing Center Nanning Branch Guangxi Nanning530004 China College of Road and Bridge Engineering Guangxi Transport Vocational and Technical College Guangxi Nanning530023 China

The erosive effect of acid rain can reduce the adhesion performance between asphalt and aggregate at the interface, leading to a decrease in the service quality of the pavement. In this study, we used the surface free energy theory to analyze the wetting behavior of asphalt on the aggregate surface both before and after acid rain erosion. We also used the sessile-drop method to calculate the adhesion work of the system and the energy index ER, and we thoroughly assessed the adhesion characteristics of the asphalt-aggregate interface by combining the pull-off test, boiled water method, and other tests. The results show that after acid rain erosion, the adhesion function of each specimen shows a different degree of reduction trend, and that the reduction trend is accompanied by the increase of erosion cycle and erosion concentration;the energy index ER value between asphalt and aggregate becomes smaller, and the more serious the acid rain erosion is, the smaller the ER value is, and the worse the adhesion is;the smaller the PH is, the more likely the spalling between asphalt-aggregate is to occur, and the easier the asphalt film is subjected to water and move. In conclusion, the presence of interfacial water plays a crucial role in reducing the strength of the bond between asphalt and aggregate. The reorganization of asphalt components on the aggregate surface by acidic ions leads to an increased polarity difference between asphalt and aggregate. This indicates that acid rain molecules can more easily penetrate the asphalt layer and encounter the aggregate, resulting in weakened adhesion and failure. In comparison, the adhesion between SBS-modified asphalt and aggregates is expected to be stronger than that of 70# petroleum asphalt. © 2024, The Authors. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Hsm2: A hybrid and scalable metadata management method in distributed file systems 10th

Hsm2: A hybrid and scalable metadata management method in di...

引用

10th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2019

作者： Wang, Yiduo Chen, Youxu Shao, Xinyang Chen, Jinzhong Yuan, Liu Xu, Yinlong School of Computer Science and Technology University of Science and Technology of China AnHui Province Key Laboratory of High Performance Computing Hefei China East China Research Institute of Electronic Engineering Hefei China China Academy of Electronics and Information Technology Beijing China

In the bigdata era, metadata performance is critical in modern distributed file systems. Traditionally, the metadata management strategies like the subtree partitioning method focus on keeping namespace locality, while the other ones like the hash-based mapping method aim to offer good load balance. Nevertheless, none of these methods achieve the two desirable properties simultaneously. To close this gap, in this paper, we propose a novel metadata management scheme, HSM2, which combines the subtree partitioning and hash-based mapping method together. We implemented HSM2 in CephFS, a widely deployed distributed file systems, and conducted a comprehensive set of metadata-intensive experiments. Experimental results show that HSM2 can achieve better namespace locality and load balance simultaneously. Compared with CephFS, HSM2 can reduce the completion time by 70% and achieve 3.9× overall throughput speedup for a file-scanning workload. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

A Node Sorting Method for K2 Algorithm in Bayesian Network Structure Learning

A Node Sorting Method for K2 Algorithm in Bayesian Network S...

引用

IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)

作者： Fan Gao Da Huang The State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China

ISBN: (数字)9781728170053

ISBN: (纸本)9781728170060

Bayesian network is an important model for reasoning in an uncertain environment. A reliable node rank is required by K2 algorithm to learn Bayesian network structure better. To provide a high-quality node rank tailored for K2 algorithm, we propose a node priority-based sorting algorithm. Given observable data only, our algorithm can be employed to learn a node rank without expert knowledge. Specifically, MCMC algorithm is first utilized to yield some Bayesian network structures that can sufficiently fit the observed data. We then define the priority of each node in these network structures. Node rank is finally obtained through weighted scoring based on the priority. The empirical results show that our sorting algorithm performs significantly better than commonly used methods, e.g., randomly sorting and MCMC algorithm, on an Asia network-learning dataset.

关键词： Bayes methods Sorting Asia Fitting Reliability Markov processes Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Nonequilibrium dynamics of the localization-delocalization transition in the non-Hermitian Aubry-André model

arXiv

引用

arXiv 2022年

作者： Zhai, Liang-Jun Huang, Guang-Yao Yin, Shuai Department of Physics Nanjing University Nanjing210093 China The School of Mathematics and Physics Jiangsu University of Technology Changzhou213001 China Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China School of Physics Sun Yat-Sen University Guangzhou510275 China

In this paper, we investigate the driven dynamics of the localization transition in the non-Hermitian Aubry-André model with the periodic boundary condition. Depending on the strength of the quasi-periodic potential λ, this model undergoes a localization-delocalization phase transition. We find that the localization length ξ satisfies ξ ∼ Ε−ν with Ε being the distance from the critical point and ν = 1 being a universal critical exponent independent of the non-Hermitian parameter. In addition, from the finite-size scaling of the energy gap between the ground state and the first excited state, we determine the dynamic exponent z as z = 2. The critical exponent of the inverse participation ratio (IPR) for the nth eigenstate is also determined as s = 0.1197. By changing Ε linearly to cross the critical point, we find that the driven dynamics can be described by the Kibble-Zurek scaling (KZS). Moreover, we show that the KZS with the same set of the exponents can be generalized to the localization phase transitions in the excited states. Copyright © 2022, The Authors. All rights reserved.

关键词： Excited states

来源：评论

学校读者我要写书评

暂无评论

InTime: Towards performance Predictability In Byzantine Fault Tolerant Proof-of-Stake Consensus

引用

Proceedings of the ACM on Management of Data 2025年第1期3卷 1-27页

作者： Weijie Sun Zihuan Xu Wangze Ni Lei Chen The Hong Kong University of Science and Technology Hong Kong Hong Kong Shenzhen Institute of Computing Sciences Shenzhen China Zhejiang University Hangzhou China The State Key Laboratory of Blockchain and Data Security Hangzhou China & Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China The Hong Kong University of Science and Technology Hong Kong Hong Kong & HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

performance predictability, ensuring low latency variability, is crucial for the reliability and efficiency of blockchain consensus. Byzantine Fault Tolerant Proof-of-Stake (BFT-PoS) consensus aims to achieve stable transaction processing latency by scheduling block generation at consistent intervals. However, BFT-PoS's incentive mechanisms grant all transaction tips to the block proposer, which can be exploited by delaying proposals to gain extra Maximal Extractable Value (MEV) rewards, thus undermining performance predictability. Existing solutions impose penalties for delays but lack a standard for measuring the extra rewards from delays or fail in malicious *** paper introduces InTime, a novel approach to safeguard performance predictability in BFT-PoS by economically motivating timely block proposals. We first introduce the untimely MEV ratio, a reliable metric to measure the extra rewards gained from proposal delays, facilitating our countermeasures against deliberate delays. Furthermore, we propose the arrival rate incentive (ARI), aligning rewards with transaction arrival timing among nodes to reduce potential MEV manipulation. To make ARI robust against malicious behaviors, we establish a committee time witness (CTW) workflow to accurately gather and verify transaction arrival times. Extensive experiments demonstrate that InTime can effectively reduce latency variability by up to 95.9%.

关键词： PoS consensus blockchain incentive design

来源：评论

学校读者我要写书评

暂无评论

TBraTS: Trusted Brain Tumor Segmentation

arXiv

引用

arXiv 2022年

作者： Zou, Ke Yuan, Xuedong Shen, Xiaojing Wang, Meng Fu, Huazhu National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Sichuan China College of Computer Science Sichuan University Sichuan China College of Mathematics Sichuan University Sichuan China Institute of High Performance Computing ASTAR Singapore Singapore

Despite recent improvements in the accuracy of brain tumor segmentation, the results still exhibit low levels of confidence and robustness. Uncertainty estimation is one effective way to change this situation, as it provides a measure of confidence in the segmentation results. In this paper, we propose a trusted brain tumor segmentation network which can generate robust segmentation results and reliable uncertainty estimations without excessive computational burden and modification of the backbone network. In our method, uncertainty is modeled explicitly using subjective logic theory, which treats the predictions of backbone neural network as subjective opinions by parameterizing the class probabilities of the segmentation as a Dirichlet distribution. Meanwhile, the trusted segmentation framework learns the function that gathers reliable evidence from the feature leading to the final segmentation results. Overall, our unified trusted segmentation framework endows the model with reliability and robustness to out-of-distribution samples. To evaluate the effectiveness of our model in robustness and reliability, qualitative and quantitative experiments are conducted on the BraTS 2019 dataset. © 2022, CC BY.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Eliminating edge electronic and phonon states of phosphorene nanoribbon by unique edge reconstruction

arXiv

引用

arXiv 2022年

作者： Li, Shi-Qi Liu, Xiangjun Wang, Xujun Liu, Hongsheng Zhang, Gang Zhao, Jijun Gao, Junfeng Ministry of Education Dalian116024 China State Key Laboratory for Modification of Chemical Fibers and Polymer Materials Institute of Micro-/Nano Electromechanical System College of Mechanical Engineering Donghua University Shanghai China Institute of High-Performance Computing A*STAR Singapore

Edge termination plays a vital role in determining the properties of 2D materials. By performing compelling ab initio simulations, a lowest-energy U-edge [ZZ(U)] reconstruction is revealed in the bilayer phosphorene. Such reconstruction reduces 60% edge energy compared with the pristine one and occurs almost without energy barrier, implying it should be the dominating edge in reality. The electronic band structure of phosphorene nanoribbon with such reconstruction resembles that of intrinsic 2D layer, exhibiting nearly edgeless band characteristics. Although ZZ(U) changes the topology of phosphorene nanoribbon (PNR), simulated TEM, STEM and STM images indicates it is very hard to be identified. One possible identify method is IR/Raman analyses because ZZ(U) edge alters vibrational modes dramatically. Beyond, it also increases the thermal conductivity of PNR 1.4 and 2.3 times than the pristine and Klein edges. Copyright © 2022, The Authors. All rights reserved.

关键词： Electronic properties

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：