检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yang, Penghui Xie, Ming-Kun Zong, Chen-Chen Feng, Lei Niu, Gang Sugiyama, Masashi Huang, Sheng-Jun College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore RIKEN Center for Advanced Intelligence Project Japan The University of Tokyo Tokyo Japan

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning. However, these methods can hardly be extended to the multi-label learning scenario, where each instance is associated with multiple semantic labels, because the prediction probabilities do not sum to one and feature maps of the whole example may ignore minor classes in such a scenario. In this paper, we propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems;on the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings. Experimental results on multiple benchmark datasets validate that the proposed method can avoid knowledge counteraction among labels, thus achieving superior performance against diverse comparing methods. Our code is available at: https://***/penghui-yang/L2D. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Significant loss suppression and large induced chirality via cooperative near- and far-field coupling in plasmonic dimer nanoantennas

arXiv

引用

arXiv 2024年

作者： Luo, Xiaoqing Huang, Rixing Lei, Dangyuan Li, Guangyuan CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Department of Materials Science and Engineering City University of Hong Kong Hong Kong999077 Hong Kong Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China

Plasmonic nanoantennas containing nano-gaps support "hotspots" for greatly enhanced light-matter interactions, but suffer from inherent high losses, a long-standing issue that hinders practical applications. Here we report a strategy to significantly suppress the losses of plasmonic dimer nanoantennas. Specifically, by introducing the concept of cooperative near- and far-field coupling, we observed an unprecedented transition from the weak coupling of localized resonances to strong coupling of collective (nonlocal) resonances, showing robustness to the gap distance between the dimer. We develop a generalized lattice sum approximation model to describe this transition and reveal its origins: the off-diagonal element of the anisotropic polarizability tensor due to near-field coupling, and the anisotropic lattice sums due to far-field coupling. This strong coupling leads to loss-suppressed plasmonic resonances with large modulation depths and meanwhile extremely high measured quality factors up to 3120 in the near-infrared regime, exceeding the record in the near infrared regime. Additionally, high-Q and large chiroptical responses can also be induced for achiral planar dimers under the critical coupling condition. This work paves an avenue toward extremely low-loss plasmonic devices, either chiral or not, for diverse important applications. © 2024, CC0.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

End-to-End Quantum Vision Transformer: Towards Practical Quantum Speedup in Large-Scale Models

arXiv

引用

arXiv 2024年

作者： Xue, Cheng Chen, Zhao-Yun Zhuang, Xi-Ning Wang, Yun-Jie Sun, Tai-Ping Wang, Jun-Chao Liu, Huan-Yu Wu, Yu-Chun Wang, Zi-Lei Guo, Guo-Ping Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Anhui Hefei230026 China CAS Center For Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Anhui Hefei230026 China Origin Quantum Computing Company Limited Anhui Hefei230088 China Institute of Advanced Technology University of Science and Technology of China Anhui Hefei230031 China Laboratory for Advanced Computing and Intelligence Engineering Zhengzhou450001 China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application University of Science and Technology of China Hefei230027 China

The field of quantum deep learning presents significant opportunities for advancing computational capabilities, yet it faces a major obstacle in the form of the "information loss problem" due to the inherent limitations of the necessary quantum tomography in scaling quantum deep neural networks. This paper introduces an end-to-end Quantum Vision Transformer (QViT), which incorporates an innovative quantum residual connection technique, to overcome these challenges and therefore optimize quantum computing processes in deep learning. Our thorough complexity analysis of the QViT reveals a theoretically exponential and empirically polynomial speedup, showcasing the model’s efficiency and potential in quantum computing applications. We conducted extensive numerical tests on modern, large-scale transformers and datasets, establishing the QViT as a pioneering advancement in applying quantum deep neural networks in practical scenarios. Our work provides a comprehensive quantum deep learning paradigm, which not only demonstrates the versatility of current quantum linear algebra algorithms but also promises to enhance future research and development in quantum deep learning1 Copyright © 2024, 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

Dynamic modeling and vibration analysis of a 6-DOFs industrial robot considering joint flexibility

Dynamic modeling and vibration analysis of a 6-DOFs industri...

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Shen, Guodong Xu, Sheng Chen, Chunjie Wang, Qiang Shandong Institute of Advanced Technology Chinese Academy of Sciences Shandong Jinan250102 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781665436786

For the industrial robots, the vibration caused by the joint flexibility could affect the manipulator's performance significantly. Therefore, the modeling and vibration analysis of industrial robot considering joint flexibility has become an important topic in recent years. However, the research on flexible-joint manipulator is usually performed for planar robots, whereas the research on general spatial multi degrees of freedom (DOFs) industrial robots are still limited. In this paper, the dynamic modeling approach is developed for vibration analysis of the serial industrial robot having six DOFs. Firstly, based on the Spong's model of joint deformation, the flexibility of all joints is considered concurrently, and the partial velocity relationship between each link and the joint are deduced. Then, the dynamic model of the 6-DOFs flexible robot is derived according to the Kane equation. The results using the proposed Kane-based method are verified by several numerical simulations. Finally, vibration responses of the end-effector under different joint stiffness parameters are analyzed. The results in this study can offer some useful guidance for the path planning and control to suppress the vibration of the multi-DOFs industrial robots. © 2021 IEEE.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporally tunable dark/bright and weak/strong mode coupling in all-dielectric DBR-metasurface-DBR structures

引用

Optics Express 2025年第12期33卷 26758-26770页

作者： Zhiyu Chang Rixing Huang Ping Chen Guangyuan Li State Key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument Taiyuan 030051 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China School of Information and Communication Engineering North University of China Taiyuan 030051 China School of Electrical Engineering Guangxi University Nanning 530004 China chenping@*** School of Medical Engineering Beijing Institute of Technology Zhuhai 519088 China gy.li@***

We report spatiotemporally tunable mode coupling between Fabry-Pérot (F-P) resonances and dark or bright modes in the weak- or strong-coupling regime in an all-dielectric coupled system, which consists of an F-P microcavity formed by two distributed Bragg reflectors (DBR) and a metasurface made of periodic nanocavities. Simulation results show that F-P resonances can be tuned to be coupled to dark waveguide modes or a bright electric dipole Mie surface lattice resonance, depending on the microcavity height, and that the coupling strength can be manipulated between the weak- and strong-coupling regimes by varying the photon lifetime, or equivalently the quality factors ( Q -factors) of F-P resonances, which can be realized by changing the number of DBR layers. We also show that the slow-light effect associated with the electromagnetically induced reflection-like window in the weak-coupling regime can also be regulated through the Q -factor. With all these findings, our study provides an alternative for manipulating light-matter interactions in coupled micro-/nano-cavities that are promising for various applications.

关键词： Bandpass filters Bragg reflectors Effective refractive index Light matter interactions Optical filters Waveguide modes

来源：评论

学校读者我要写书评

暂无评论

A framework of cooperative UAV-UGV system for target tracking

A framework of cooperative UAV-UGV system for target trackin...

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Su, Zhilong Wang, Can Wu, Xinyu Dong, Yao Ni, Jiangpeng He, Bailin Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Beijing100049 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781665436786

This paper proposed a framework of cooperative UAV-UGV system. This system consists of three modules: UAV, UGV, and ground station console. It has the characteristics of high cohesion, low coupling, cross platform, and cross language. Compared with the prior methods which UAV-UGV cooperation system that only uses UAV to track UGV, our method is more effective and can give full play to the advantages of UAV and UGV. We use UAV visual tracking algorithm and coordinate transformation to get the target location, and use UGV to navigate to the target location to keep up with the target. The high mobility of UAV makes the target tracking range of the whole system larger, the robustness of UGV is good, and the tasks can be performed more precisely. © 2021 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

A data-driven shared control system for exoskeleton rehabilitation robot

A data-driven shared control system for exoskeleton rehabili...

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Li, Feng He, Yong Li, Jinke Ni, Jiangpeng Wu, Xinyu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China

ISBN: (纸本)9781665436786

It is very important to establish a control operating system for rehabilitation robots, especially to improve the rehabilitation effect and human-machine interaction ability of patients. Exoskeletons have been proved to be effective in providing highly repeatable and accurate rehabilitation exercises, but most existing exoskeletons have inconsistent operating systems and data loss. This paper designed a novel data-driven shared control system(DDSCS) farmework, applied to different exoskeleton rehabilitation robots (ERR). Due to the unique physical characteristics of exoskeleton rehabilitation robots, it can't be adapt to different patients. Firstly, the DDSCS framework is established via the data-driven and shared technology, and the feasibility is analyzed. Secondly, to iterate the individualized gait trajectory, data-driven gait trajectory correction model is designed. Finally, the shared human-machine interface is developed, and the superiority and effectiveness of DDSCS framework are verified by the exoskeleton robot experiments. © 2021 IEEE.

关键词： Control systems

来源：评论

学校读者我要写书评

暂无评论

Predictive Feature Learning for Future Segmentation Prediction

Predictive Feature Learning for Future Segmentation Predicti...

引用

International Conference on Computer Vision (ICCV)

作者： Zihang Lin Jiangxin Sun Jian-Fang Hu Qizhi Yu Jian-Huang Lai Wei-Shi Zheng Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Zhejiang Laboratory China Pengcheng Laboratory China

ISBN: (纸本)9781665428132

Future segmentation prediction aims to predict the segmentation masks for unobserved future frames. Most existing works addressed it by directly predicting the intermediate features extracted by existing segmentation models. However, these segmentation features are learned to be local discriminative (with rich details) and are always of high resolution/dimension. Hence, the complicated spatiotemporal variations of these features are difficult to predict, which motivates us to learn a more predictive representation. In this work, we develop a novel framework called Predictive Feature Autoencoder. In the proposed framework, we construct an autoencoder which serves as a bridge between the segmentation features and the predictor. In the latent feature learned by the autoencoder, global structures are enhanced and local details are suppressed so that it is more predictive. In order to reduce the risk of vanishing the suppressed details during recurrent feature prediction, we further introduce a reconstruction constraint in the prediction module. Extensive experiments show the effectiveness of the proposed approach and our method outperforms state-of-the-arts by a considerable margin.

关键词： Representation learning Bridges Computer vision Predictive models Feature extraction Decoding Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Brain Functional Network Generation Using Distribution-Regularized Adversarial Graph Autoencoder with Transformer for Dementia Diagnosis

引用

Computer Modeling in Engineering & Sciences 2023年第12期137卷 2129-2147页

作者： Qiankun Zuo Junhua Hu Yudong Zhang Junren Pan Changhong Jing Xuhang Chen Xiaobo Meng Jin Hong School of Information Engineering Hubei University of EconomicsWuhan430205China State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin China Institute of Water Resources and Hydropower ResearchBeijing100038China School of Computing and Mathematic Sciences University of LeicesterLeicesterLE17RHUK Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518055China Faculty of Science and Technology University of MacaoMacao999078China School of Geophysics Chengdu University of TechnologyChengdu610059China Laboratory of Artificial Intelligence and 3D Technologies for Cardiovascular Diseases Guangdong Provincial Key Laboratory of South China Structural Heart DiseaseGuangdong Provincial People’s Hospital(Guangdong Academy of Medical Sciences)Southern Medical UniversityGuangzhou519041China Medical Research Institute Guangdong Provincial People’s Hospital(Guangdong Academy of Medical Sciences)Southern Medical UniversityGuangzhou519041China

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia *** brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia ***,it is challenging to access considerable amounts of brain functional network data,which hinders the widespread application of data-driven models in dementia *** this study,a novel distribution-regularized adversarial graph auto-Encoder(DAGAE)with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset,improving the dementia diagnosis accuracy of data-driven ***,the label distribution is estimated to regularize the latent space learned by the graph encoder,which canmake the learning process stable and the learned representation ***,the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain *** typical topological properties and discriminative features can be preserved ***,the generated brain functional networks improve the prediction performance using different classifiers,which can be applied to analyze other cognitive *** on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset demonstrate that the proposed model can generate good brain functional *** classification results show adding generated data can achieve the best accuracy value of 85.33%,sensitivity value of 84.00%,specificity value of 86.67%.The proposed model also achieves superior performance compared with other related ***,the proposedmodel effectively improves cognitive disease diagnosis by generating diverse brain functional networks.

关键词： Adversarial graph encoder label distribution generative transformer functional brain connectivity graph convolutional network dementia

来源：评论

学校读者我要写书评

暂无评论

TactCapsNet: Tactile capsule network for object hardness recognition

TactCapsNet: Tactile capsule network for object hardness rec...

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Fang, Senlin Mi, Tingting Zhou, Zhenning Ye, Chaoxiang Liu, Chengliang Wu, Hancheng Yi, Zhengkun Wu, Xinyu Shenzhen Institute of Advanced Technology CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China Shenzhen Key Laboratory of Smart Sensing and Intelligent Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

ISBN: (纸本)9781665436786

Hardness is one of the most essential tactile clues for robots to recognize objects. However, methods for robots to recognize hardness are limited. In this paper, based on the Capsule Network (CapsNet), we propose a novel tactile capsule network (TactCapsNet) for object hardness recognition. Specifically, we collect a tactile dataset on the silicone samples with three different shapes, and the silicone samples of each shape have thirteen hardness levels ranging from 0A (Shore A scale) to 60A at 5A intervals. Furthermore, we construct the tactile image as the input of the CapsNet to make full use of the spatio-temporal information of the tactile hardness dataset. The experimental results prove that the proposed approach achieves higher accuracy and quadratic weighted kappa (QWK) than support vector machine (SVM), long short-term memory (LSTM), convolutional neural network (CNN), and CapsNet. © 2021 IEEE.

关键词： Hardness

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：