检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Tang, Jialiang Chen, Shuo Niu, Gang Sugiyama, Masashi Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan The Graduate School of Frontier Sciences The University of Tokyo Japan

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some privacy issues and data management considerations. Therefore, data-free knowledge distillation approaches proposed to collect training instances from the Internet. However, most of them have ignored the common distribution shift between the instances from original training data and webly collected data, affecting the reliability of the trained student network. To solve this problem, we propose a novel method dubbed "Knowledge Distillation between Different Distributions" (KD3), which consists of three components. Specifically, we first dynamically select useful training instances from the webly collected data according to the combined predictions of teacher network and student network. Subsequently, we align both the weighted features and classifier parameters of the two networks for knowledge memorization. Meanwhile, we also build a new contrastive learning block called MixDistribution to generate perturbed data with a new distribution for instance alignment, so that the student network can further learn a distribution-invariant representation. Intensive experiments on various benchmark datasets demonstrate that our proposed KD3 can outperform the state-of-the-art data-free knowledge distillation approaches. 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

Distribution Shift Matters for Knowledge Distillation with Webly Collected Images

Distribution Shift Matters for Knowledge Distillation with W...

引用

International Conference on computer Vision (ICCV)

作者： Jialiang Tang Shuo Chen Gang Niu Masashi Sugiyama Chen Gong School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan The Graduate School of Frontier Sciences The University of Tokyo Japan

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some privacy issues and data management considerations. Therefore, data-free knowledge distillation approaches proposed to collect training instances from the Internet. However, most of them have ignored the common distribution shift between the instances from original training data and webly collected data, affecting the reliability of the trained student network. To solve this problem, we propose a novel method dubbed "Knowledge Distillation between Different Distributions" (KD 3 ), which consists of three components. Specifically, we first dynamically select useful training instances from the webly collected data according to the combined predictions of teacher network and student network. Subsequently, we align both the weighted features and classifier parameters of the two networks for knowledge memorization. Meanwhile, we also build a new contrastive learning block called MixDistribution to generate perturbed data with a new distribution for instance alignment, so that the student network can further learn a distribution-invariant representation. Intensive experiments on various benchmark datasets demonstrate that our proposed KD 3 can outperform the state-of-the-art data-free knowledge distillation approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compression for qubit clocks

arXiv

引用

arXiv 2022年

作者： Yang, Yuxiang Chiribella, Giulio Hayashi, Masahito Department of Computer Science The University of Hong Kong Hong Kong Department of Computer Science The University of Oxford United Kingdom Canadian Institute for Advanced Research CIFAR Program in Quantum Information Science Canada Graduate School of Mathematics Nagoya University Japan Centre for Quantum Technologies National University of Singapore Singapore

Two-level (qubit) clock systems are often used to perform precise measurement of time. In this work, we propose a compression protocol for n identically prepared states of qubit clocks. The protocol faithfully encodes the states into (1/2) log n qubits and (1/2) log n classical bits and works even in the presence of noise. If the purity of the clock states is fixed, (1/2) log n qubits are sufficient. We also prove that this protocol requires the minimum amount of total memory among all protocols with vanishing error in the large n limit. Copyright © 2022, The Authors. All rights reserved.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

A Survey on Applications of Large Language Model-Driven Digital Twins for Intelligent Network Optimization

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Guo, Zhiqi Tang, Fengxiao Luo, Linfeng Zhao, Ming Kato, Nei Central South University School of Computer Science and Engineering Changsha410000 China Tohoku University Graduate School of Information Sciences Japan

With the widespread application of digital twin (DT) technology in network optimization and intelligent management, its integration with large language models (LLMs) presents immense potential. LLMs excel in natural language processing, multimodal analysis, and real-time optimization, enabling innovative solutions for intelligent monitoring, resource allocation, and decision-making in complex network environments. This paper systematically reviews the development of DTs and LLMs, elaborates on their core principles and application scenarios, and examines the capabilities of LLM-driven DTs in key network optimization tasks, including traffic prediction, fault diagnosis, resource allocation, and multi-objective optimization. By leveraging real-time data from DTs, LLMs can dynamically generate optimization strategies, enabling precise monitoring and intelligent tuning. Furthermore, this paper explores the potential of integrating LLMs and DTs to address complex challenges such as data quality, latency sensitivity, and energy consumption demands, while summarizing existing technical bottlenecks. Finally, the paper proposes several potential research directions to address these challenges, offering a comprehensive perspective for advancing the efficiency and automation of next-generation intelligent networks. © 1998-2012 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Dam Water Overflow Estimation using Time Series 9

Dam Water Overflow Estimation using Time Series

引用

9th IEEE Global Conference on Consumer Electronics, GCCE 2020

作者： Khin, Mie Mie Tin, Mie Mie Zin, Thi Thi Tin, Pyke Computer University Meiktila Meiktila Myanmar Faculty of Information Science Mandalay Myanmar University of Miyazaki Graduate School of Engineering Miyazaki Japan

ISBN: (纸本)9781728198026

This paper will implement the water level estimation of the dam from Myanmar. We use the time series stochastic model to calculate the water level estimation varying on in flow and consumption of dam. This approach is applying probability of Markovian Time Series. This paper based on rainfall and the other factors of dam water storage such as inflow and outflow of dam. This result estimate actual monthly water spread area and shows error is small. This research result also highlight that Markovian Time Series model is one of the best estimate processes for water level estimation. © 2020 IEEE.

关键词： Dams

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Medical Image Fusion Method Incorporating an Adaptive Attention Mechanism

A Multimodal Medical Image Fusion Method Incorporating an Ad...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yingxian Zhang Yushui Geng Hu Liang Hai Zhong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China Department of Radiology The Second Hospital of Shandong University Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Multimodal medical image fusion technology provides more comprehensive and accurate image support for clinical diagnosis and treatment by integrating complementary information from different imaging modalities. Aiming at the problem that existing methods are still insufficient in detail feature extraction and inter-modal information fusion, this paper proposes a multimodal medical image fusion method combined with an adaptive attention mechanism. First, we design the Grouped Receptive Field Attentional Convolution (GRFAConv) to solve the problem of insufficient detail feature extraction capability. With the multi-head receptive field adaptive weighting strategy of grouped convolution, the range and weight of the receptive field of the convolution kernel can be adaptively adjusted according to the different demands of local and global features of the image to improve the effect of detail retention. Second, for the problem of information fusion between different modalities, we introduce an improved CBAM attention module in the feature fusion process, which adaptively selects and enhances the features in the key regions through the channel attention and spatial attention mechanisms, which greatly improves the clarity of the fused image details and the accuracy of the information expression in the key regions. Furthermore, experimental results on several medical image datasets show that the algorithm proposed in this paper can generate relatively high-quality fused images. It not only enriches the detailed features of the image, but also achieves significant advantages in several evaluation metrics.

关键词： Measurement Attention mechanisms Accuracy Convolution Federated learning Feature extraction Clinical diagnosis Kernel Medical diagnostic imaging Image fusion

来源：评论

学校读者我要写书评

暂无评论

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

arXiv

引用

arXiv 2023年

作者： Yang, Siyuan Liu, Jun Lu, Shijian Hwa, Er Meng Kot, Alex C. Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore School of Computer Science & Engineering Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatialtemporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Analysis of Rehabilitation Methods for Small Dogs Based on the Muscular Activity

Analysis of Rehabilitation Methods for Small Dogs Based on t...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Daisuke Chugo Yujie Li Satoshi Muramatsu Sho Yokota Jin-Hua She Hiroshi Hashimoto Hiroaki Kamishina Hiroyuki Hirabayashi Graduate School of Science and Technology Kwansei Gakuin University Sanda Hyogo Japan School of Information Science and Technology Tokai University Hiratsuka Kanagawa Japan Faculty of Science and Engineering Toyo University Kawagoe Saitama Japan School of Engineering Tokyo University of Technology Hachioji Tokyo Japan Master Program of Innovation for Design and Engineering Advanced Institute of Industrial Technology Shinagawa Tokyo Japan KyotoAR Animal Advanced Medical Center Kuse Kyoto Japan Sakura Animal Hospital Yatomi Aichi Japan

In recent years, with the increase in the number of dogs, paralysis of the lower limbs due to herniated discs in dogs has become a problem. There is no fundamental cure for this condition, and the main treatment is physical therapy. Usually, these dogs need physical therapy with a physical therapist every day, but it’s not realistic. Therefore, it is required that the owner be effective rehabilitation at home. However, quantitative evaluation methods have not been established for physiotherapy because physiotherapy is performed by veterinarians based on their experience. In this paper, we proposes a musculoskeletal model of the dog’s lower limb to analyze the dynamics of rehabilitation movements and confirm its validity by comparing the muscular activity obtained from the model with the measured EMG data. Using proposed model, we performed a simulation experiment to discuss the relationship between the timing of the input force and muscular activity by changing the timing of the input force. From the data obtained in the experiment, we investigated the relationship between the timing of the input force and the muscular activity and clarify how to input a support force for the physical therapy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Partial gathering of mobile agents in dynamic rings

arXiv

引用

arXiv 2022年

作者： Shibata, Masahiro Sudo, Yuichi Nakamura, Junya Kim, Yonghwan Graduate school of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Fukuoka Iizuka820-8502 Japan Graduate School of Computer and Information Sciences Hosei University Koganei-shi 3-7-2 Kajino-cho Tokyo184-8584 Japan Information and Media Center Toyohashi University of Technology 1-1 Hibarigaoka Tempaku-cho Aichi Toyohashi441-8580 Japan Graduate School of Computer Science and Engineering Nagoya Institute of Technology Gokiso-cho Showa-ku Aichi Nagoya466-8555 Japan

In this paper, we consider the partial gathering problem of mobile agents in synchronous dynamic bidirectional ring networks. The partial gathering problem is a generalization of the (well-investigated) total gathering problem, which requires that all k agents distributed in the network terminate at a non-predetermined single node. The partial gathering problem requires, for a given positive integer g ( © 2022, CC BY.

关键词： Mobile agents

来源：评论

学校读者我要写书评

暂无评论

Parameters fixing strategy for quantum approximate optimization algorithm

arXiv

引用

arXiv 2021年

作者： Lee, Xinwei Saito, Yoshiyuki Cai, Dongsheng Asai, Nobuyoshi Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan Graduate School of Computer Science and Engineering University of Aizu Fukushima Aizu-Wakamatsu Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Ibaraki Japan School of Computer Science and Engineering University of Aizu Fukushima Aizu-Wakamatsu Japan

The quantum approximate optimization algorithm (QAOA) has numerous promising applications in solving the combinatorial optimization problems on near-term Noisy Intermediate Scalable Quantum (NISQ) devices. QAOA has a quantum-classical hybrid structure. Its quantum part consists of a parameterized alternating operator ansatz, and its classical part comprises an optimization algorithm, which optimizes the parameters to maximize the expectation value of the problem Hamiltonian. This expectation value depends highly on the parameters, this implies that a set of good parameters leads to an accurate solution. However, at large circuit depth of QAOA, it is difficult to achieve global optimization due to the multiple occurrences of local minima or maxima. In this paper, we propose a parameters fixing strategy which gives high approximation ratio on average, even at large circuit depths, by initializing QAOA with the optimal parameters obtained from the previous depths. We test our strategy on the Max-cut problem of certain classes of graphs such as the 3-regular graphs and the ErdÖs-Rényi graphs. © 2021, CC BY.

关键词： Global optimization

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：