检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ge, Shiming Zhao, Shengwei Li, Chenyu Zhang, Yu Li, Jia The Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China SenseTime Group Limited 100084 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China The Peng Cheng Laboratory Shenzhen518055 China

Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a bridge distillation approach to turn a complex face model pretrained on private high-resolution faces into a light-weight one for low-resolution face recognition. In our approach, such a cross-dataset resolution-adapted knowledge transfer problem is solved via two-step distillation. In the first step, we conduct cross-dataset distillation to transfer the prior knowledge from private high-resolution faces to public high-resolution faces and generate compact and discriminative features. In the second step, the resolution-adapted distillation is conducted to further transfer the prior knowledge to synthetic low-resolution faces via multi-task learning. By learning low-resolution face representations and mimicking the adapted high-resolution knowledge, a light-weight student model can be constructed with high efficiency and promising accuracy in recognizing low-resolution faces. Experimental results show that the student model performs impressively in recognizing low-resolution faces with only 0.21M parameters and 0.057MB memory. Meanwhile, its speed reaches up to 14,705, 934 and 763 faces per second on GPU, CPU and mobile phone, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

PipePar: A Pipelined Hybrid Parallel Approach for Accelerating Distributed DNN Training

PipePar: A Pipelined Hybrid Parallel Approach for Accelerati...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jiange Li Yuchen Wang Jinghui Zhang Jiahui Jin Fang Dong Lei Qian School of Computer Science and Engineering Southeast University Nanjing P.R. China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi P.R. China

Large scale DNN training tasks are exceedingly compute-intensive and time-consuming, which are usually executed on highly-parallel platforms. Data and model parallelization is a common way to speed up the training progress across devices. However, they tend to achieve sub-optimal performance due to the communication overheads and unbalanced load among servers. Recent emerging pipelining solutions mitigate the above issues, incorporating the advantages of data and model parallelism. In this paper, we make a step further towards optimizing the execution of pipelining. We introduce PipePar, a pipeline-parallel DNN training method that provides optimized execution strategies of layer-stacked DNNs. PipePar considers the entire tensor partition space of pipelining and explores potential hybrid parallel configurations of each stage in the pipeline. Additionally, we notice the network heterogeneity between different GPU servers and it is inevitable to transfer tensors with different bandwidths and latency. So, taking into account both computation and communication capacity of different GPU servers, PipePar is intended to find a elastic load distribution strategy at different levels. We evaluate PipePar with a set of real-world DNNs on 4 GPU servers. Our experimental results show that PipePar is able to find an efficient strategy that are up to 2.16× faster than state-of-the-art hybrid parallelization approaches.

关键词： Training Performance evaluation Tensors Computational modeling Graphics processing units Data models Servers

来源：评论

学校读者我要写书评

暂无评论

Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson’s Disease Screening in OCT

arXiv

引用

arXiv 2025年

作者： Zhang, Xiaoqing Shi, Hanfeng Li, Xiangyu Ye, Haili Xu, Tao Li, Na Hu, Yan Lv, Fan Chen, Jiangfan Liu, Jiang Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China State Key Laboratory of Ophthalmology Optometry and Vision Science Wenzhou Medical University Wenzhou China Centre for Computational Science and Mathematical Modelling Coventry University Coventry United Kingdom School of Computer Science University of Nottingham Ningbo China Ningbo315100 China School of Ophthalmology and Optometry Wenzhou Medical University Wenzhou325035 China Department of Electronic and Information Engineering Changchun University Changchun130022 China

Parkinson’s disease (PD) is a prevalent neurodegenerative disorder globally. The eye’s retina is an extension of the brain and has great potential in PD screening. Recent studies have suggested that texture features extracted from retinal layers can be adopted as biomarkers for PD diagnosis under optical coherence tomography (OCT) images. Frequency domain learning techniques can enhance the feature representations of deep neural networks (DNNs) by decomposing frequency components involving rich texture features. Additionally, previous works have not exploited texture features for automated PD screening in OCT. Motivated by the above analysis, we propose a novel Adaptive Wavelet Filter (AWF) that serves as the Practical Texture Feature Amplifier to fully leverage the merits of texture features to boost the PD screening performance of DNNs with the aid of frequency domain learning. Specifically, AWF first enhances texture feature representation diversities via channel mixer, then emphasizes informative texture feature representations with the well-designed adaptive wavelet filtering token mixer. By combining the AWFs with the DNN stem, AWFNet is constructed for automated PD screening. Additionally, we introduce a novel Balanced Confidence (BC) Loss by mining the potential of sample-wise predicted probabilities of all classes and class frequency prior, to further boost the PD screening performance and trustworthiness of AWFNet. The extensive experiments manifest the superiority of our AWFNet and BC over state-of-the-art methods in terms of PD screening performance and trustworthiness. © 2025, CC BY-NC-SA.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Field-tuned magnetic structure and phase diagram of the honeycomb magnet YbCl_(3)

引用

Science China(Physics,Mechanics & Astronomy) 2021年第3期64卷 84-89页

作者： YiQing Hao HongLiang Wo YiMeng Gu XiaoWen Zhang YiQing Gu ShiYi Zheng Yang Zhao GuangYong Xu Jeffrey WLynn Kenji Nakajima Naoki Murai WenBin Wang Jun Zhao State Key Laboratory of Surface Physics and Department of Physics Fudan UniversityShanghai 200433China NIST Center for Neutron Research National Institute of Standards and TechnologyGaithersburg 20899USA Department of Materials Science and Engineering University of MarylandCollege Park 20742USA J-PARC Center Japan Atomic Energy Agency(JAEA)Ibaraki 319-1195Japan Institute of Nanoelectronic Devices and Quantum Computing Fudan UniversityShanghai 200433China Collaborative Innovation Center of Advanced Microstructures Nanjing 210093China

We report thermodynamic and neutron diffraction measurements on the magnetic ordering properties of the honeycomb lattice magnet YbCl_(3). We find YbCl_(3) exhibits a Ne′el type long-range magnetic order at the wavevector(0, 0, 0) below TN= 600 *** magnetic order is associated with a small sharp peak in heat capacity and most magnetic entropy release occurs above the magnetic ordering temperature. The magnetic moment lies in-plane, parallel to the monoclinic a-axis, whose magnitude mYb= 0.86(3) μBis considerably smaller than the expected fully ordered moment of 2.24 μBfor the doublet crystal-field ground state. The magnetic ordering moment gradually increases with increasing magnetic field perpendicular to the ab-plane, reaching a maximum value of 1.6(2) μBat 4 T, before it is completely suppressed above ~ 9 T. These results indicate the presence of strong quantum fluctuations in YbCl_(3).

关键词： magnetic order neutron diffraction honeycomb lattice

来源：评论

学校读者我要写书评

暂无评论

Thin-film neural networks for optical inverse problem

引用

Light(advanced Manufacturing) 2021年第4期2卷 23-30页

作者： Lingjie Fan Ang Chen Tongyu Li Jiao Chu Yang Tang Jiajun Wang Maoxiong Zhao Tangyao Shen Minjia Zheng Fang Guan Haiwei Yin Lei Shi Jian Zi State Key Laboratory of Surface Physics Key Laboratory of Micro-and Nano-Photonic Structures(Ministry of Education)and Department of PhysicsFudan UniversityShanghai 200433China Shanghai Engineering Research Center of Optical Metrology for Nano-fabrication(SERCOM) Shanghai 200433China Institute for Nanoelectronic devices and Quantum computing Fudan UniversityShanghai 200438China Collaborative Innovation Center of Advanced Microsstructures Nanjing UniversityNanjing 210093China

The thin-film optical inverse problem has attracted a great deal of attention in science and industry,and is widely applied to optical ***,as the number of layers increases,the time it takes to extract the parameters of thin films drastically ***,we introduce the idea of exploiting the structural similarity of all-optical neural networks and applied it to the optical inverse *** propose thin-film neural networks(TFNNs)to efficiently adjust all the parameters of multilayer thin *** test the performance of TFNNs,we implemented a TFNN algorithm,and a reflectometer at normal incidence was *** on multilayer thin films with 232 layers,it is shown that TFNNs can reduce the time consumed by parameter extraction,which barely increased with the number of layers compared with the conventional *** were also used to design multilayer thin films to mimic the optical response of three types of cone cells in the human *** light passing through these multilayer thin films was then recorded as a colored photo.

关键词： method inverse film

来源：评论

学校读者我要写书评

暂无评论

Gender-Based Deep Learning Firefly Optimization Method for Test Data Generation

引用

Computational Intelligence and Neuroscience 2021年 2021卷 8056225-8056225页

作者： Zhang, Wenning Jiao, Chongyang Zhou, Qinglei Liu, Yang Xu, Ting State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Henan450000 China Software College Zhongyuan University of Technology Zhengzhou Henan450000 China School of Information Engineering Zhengzhou University Zhengzhou Henan450000 China The Jackson Laboratory for Genomic Medicine FarmingtonCT06032 United States

Software testing is a widespread validation means of software quality assurance in industry. Intelligent optimization algorithms have been proved to be an effective way of automatic test data generation. Firefly algorithm has received extensive attention and been widely used to solve optimization problems because of less parameters and simple implement. To overcome slow convergence rate and low accuracy of the firefly algorithm, a novel firefly algorithm with deep learning is proposed to generate structural test data. Initially, the population is divided into male subgroup and female subgroup. Following the randomly attracted model, each male firefly will be attracted by another randomly selected female firefly to focus on global search in whole space. Each female firefly implements local search under the leadership of the general center firefly, constructed based on historical experience with deep learning. At the final period of searching, chaos search is conducted near the best firefly to improve search accuracy. Simulation results show that the proposed algorithm can achieve better performance in terms of success coverage rate, coverage time, and diversity of solutions. © 2021 Wenning Zhang et al.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Polarization-Orthogonal Nondegenerate Plasmonic Higher-Order Topological states

引用

Physical Review Letters 2023年第21期130卷 213603-213603页

作者： Yuanzhen Li Su Xu Zijian Zhang Yumeng Yang Xinrong Xie Wenzheng Ye Feng Liu Haoran Xue Liqiao Jing Zuojia Wang Qi-Dai Chen Hong-Bo Sun Erping Li Hongsheng Chen Fei Gao Interdisciplinary Center for Quantum Information State Key Laboratory of Extreme Photonics and Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou 310027 China International Joint Innovation Center The Electromagnetics Academy at Zhejiang University Zhejiang University Haining 314400 China Key Laboratory of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang Jinhua Institute of Zhejiang University Zhejiang University Jinhua 321099 China State Key Laboratory of Integrated Optoelectronics College of Electronic Science and Engineering Jilin University 2699 Qianjin Street Changchun 130012 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore 637371 Singapore State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision Instrument Tsinghua University Haidian Beijing 100084 China Shaoxing Institute of Zhejiang University Zhejiang University Shaoxing 312000 China

Photonic topological states, providing light-manipulation approaches in robust manners, have attracted intense attention. Connecting photonic topological states with far-field degrees of freedom (d.o.f.) has given rise to fruitful phenomena. Recently emerged higher-order topological insulators (HOTIs), hosting boundary states two or more dimensions lower than those of bulk, offer new paradigms to localize or transport light topologically in extended dimensionalities. However, photonic HOTIs have not been related to d.o.f. of radiation fields yet. Here, we report the observation of polarization-orthogonal second-order topological corner states at different frequencies on a designer-plasmonic kagome metasurface in the far field. Such phenomenon stands on two mechanisms, i.e., projecting the far-field polarizations to the intrinsic parity d.o.f. of lattice modes and the parity splitting of the plasmonic corner states in spectra. We theoretically and numerically show that the parity splitting originates from the underlying interorbital coupling. Both near-field and far-field experiments verify the polarization-orthogonal nondegenerate second-order topological corner states. These results promise applications in robust optical single photon emitters and multiplexed photonic devices.

关键词： Metasurfaces Topological effects in photonic systems

来源：评论

学校读者我要写书评

暂无评论

A Brief Introduction to Manifold Optimization

引用

Journal of the Operations Research Society of China 2020年第2期8卷 199-248页

作者： Jiang Hu Xin Liu Zai-Wen Wen Ya-Xiang Yuan Beijing International Center for Mathematical Research Peking UniversityBeijing 100871China State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100190China

Manifold optimization is ubiquitous in computational and appliedmathematics,statistics,engineering,machine learning,physics,chemistry,*** of the main challenges usually is the non-convexity of the manifold *** utilizing the geometry of manifold,a large class of constrained optimization problems can be viewed as unconstrained optimization problems on *** this perspective,intrinsic structures,optimality conditions and numerical algorithms for manifold optimization are *** recent progress on the theoretical results of manifold optimization is also presented.

关键词： Convergence First-order-type algorithms Manifold optimization Retraction Second-order-type algorithms

来源：评论

学校读者我要写书评

暂无评论

Arbitrary coherent distributions in a programmable quantum walk

引用

Physical Review Research 2022年第2期4卷 023042-023042页

作者： Rong Zhang Ran Yang Jian Guo Chang-Wei Sun Yi-Chen Liu Heng Zhou Ping Xu Zhenda Xie Yan-Xiao Gong Shi-Ning Zhu National Laboratory of Solid State Microstructure School of Physics School of Electronic Science and Engineering and Collaborative Innovation Center of Advanced Microstructures Nanjing University Nanjing 210093 China College of Electronic and Optical Engineering Nanjing University of Posts and Telecommunication Nanjing 210023 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu 611731 China Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computing National University of Defense Technology Changsha 410073 China

The coherent superposition of position states in a quantum walk (QW) can be precisely engineered towards the desired distributions to meet the need of quantum information applications. The coherent distribution can make full use of quantum parallel in computation and simulation. Particularly, the uniform superposition provides the robust nonlocality, which has wide applications such as the generation of genuine multibit random numbers without postprocessing. We experimentally demonstrate that the rich dynamics featured with arbitrary coherent distributions can be obtained by introducing different sets of the time- and position-dependent operations. Such a QW is realized by a resource-constant and flexible optical circuit, in which the variable operation is executed based on a Sagnac interferometer in an intrinsically stable and precisely controlled way. Our results contribute to the practical realization of quantum-walk-based quantum computation, quantum simulations, and quantum information protocols.

关键词： Quantum control Quantum information architectures & platforms Quantum protocols

来源：评论

学校读者我要写书评

暂无评论

AFDM-Enabled Integrated Sensing and Communication: Theoretical Framework and Pilot Design

arXiv

引用

arXiv 2025年

作者： Zhang, Fan Wang, Zhaocheng Mao, Tianqi Jiao, Tianyu Zhuo, Yinxiao Wen, Miaowen Xiang, Wei Chen, Sheng Karagiannidis, George K. Department of Electronic Engineering Tsinghua University Beijing100084 China State Key Laboratory of CNS/ATM Beijing Institute of Technology Beijing100081 China Zhuhai519088 China School of Electronic and Information Engineering South China University of Technology Guangzhou China School of Computing Engineering and Mathematical Sciences La Trobe University MelbourneVIC3086 Australia School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Greece

The integrated sensing and communication (ISAC) has been envisioned as one representative usage scenario of sixth-generation (6G) network. However, the unprecedented characteristics of 6G, especially the doubly dispersive channel, make classical ISAC waveforms rather challenging to guarantee a desirable performance level. The recently proposed affine frequency division multiplexing (AFDM) can attain full diversity even under doubly dispersive effects, thus becoming a competitive candidate for next-generation ISAC waveforms. Relevant investigations are still at an early stage, which involve only straightforward design lacking explicit theoretical analysis. This paper provides an in-depth investigation on AFDM waveform design for ISAC applications. Specifically, the closed-form Crámer-Rao bounds of target detection for AFDM are derived, followed by a demonstration on its merits over existing counterparts. Furthermore, we formulate the ambiguity function of the pilot-assisted AFDM waveform for the first time, revealing conditions for stable sensing performance. To further enhance both the communication and sensing performance of the AFDM waveform, we propose a novel pilot design by exploiting the characteristics of AFDM signals. The proposed design is analytically validated to be capable of optimizing the ambiguity function property and channel estimation accuracy simultaneously as well as overcoming the sensing and channel estimation range limitation originated from the pilot spacing. Numerical results have verified the superiority of the proposed pilot design in terms of dual-functional performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Cramer-Rao bounds

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：