检索结果-内蒙古大学图书馆

Implicit Multi-Scale Swin Transformer Network for Image Denoising

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Qi Ding, Yuwei Zhang, Weiqi Zhu, Yian Zhang, Bob Lin, Jerry Chun-Wei Harbin Institute of Technology at Weihai School of Economics and Management Weihai China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Northwestern Polytechnical University School of Computer Science Xi’an China Northwestern Polytechnical University Yangtze River Delta Research Institute Taicang China University of Macau PAMI Research Group Department of Computer and Information Science Taipa China Department of Distributed Systems and IT Devices Electrical Engineering and Mathematical Sciences Silesian university of technology Poland

Image denoising has been used in various edge computing scenarios such as consumer electronics to improve the image quality and user experience. Existing image denoising methods based on Convolutional Neural Networks (CNNs) and vision Transformers achieve good performance by empirically utilizing residual neural network (ResNet) as basic component. However, ResNet lacks interpretability in network design and also long-term memory of features, potentially restricting the performance of denoising networks. In this paper, we propose an Implicit Multi-scale Swin Transformer Network (IMSNet) for image denoising, which introduces the implicit Euler scheme from the feature memory perspective. Specifically, densely connected implicit feature extraction blocks (IFEBs) are designed to learn the residual mapping between noisy and clean images. The IFEB reformulates the initial skip connection of ResNet based on the implicit Euler discretization, providing both network interpretability and long-term memory. In IFEB, the multi-scale swin Transformer block (MSB) is designed as the implicit layer to capture spatial details and non-local contextual information at different scales. Additionally, a cross-layer feature fusion block (CLFF) is proposed to further improve feature reuse capabilities. Compared to existing denoising networks, the extensive experiments demonstrate the superior performance of our IMSNet in various image denoising tasks, and the flexibility in the practical applications with proposed light model on resource-restricted platforms such as consumer electronic devices. © 1975-2011 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Federated Optimization of Smooth Loss Functions

arXiv

引用

arXiv 2022年

作者： Jadbabaie, Ali Makur, Anuran Shah, Devavrat The Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Computer Science The Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States

In this work, we study empirical risk minimization (ERM) within a federated learning framework, where a central server seeks to minimize an ERM objective function using n samples of training data that is stored across m clients and the server. The recent flurry of research in this area has identified the Federated Averaging (FedAve) algorithm as the staple for determining ϵ-approximate solutions to the ERM problem. Similar to standard optimization algorithms, e.g., stochastic gradient descent, the convergence analysis of FedAve and its variants only relies on smoothness of the loss function in the optimization parameter. However, loss functions are often very smooth in the training data too. To exploit this additional smoothness in data in a federated learning context, we propose the Federated Low Rank Gradient Descent (FedLRGD) algorithm. Since smoothness in data induces an approximate low rank structure on the gradient of the loss function, our algorithm first performs a few rounds of communication between the server and clients to learn weights that the server can use to approximate clients' gradients using its own gradients. Then, our algorithm solves the ERM problem at the server using an inexact gradient descent method. To theoretically demonstrate that FedLRGD can have superior performance to FedAve, we present a notion of federated oracle complexity as a counterpart to canonical oracle complexity in the optimization literature. Under some assumptions on the loss function, e.g., strong convexity and smoothness in the parameter, η-Hölder class smoothness in the data, etc., we prove that the federated oracle complexity of FedLRGD scales like (Equation presented) and that of FedAve scales like (Equation presented) (neglecting typically sub-dominant factors), where 1 is the ratio of client-to-server communication time to gradient computation time, p is the parameter dimension, and d is the data dimension. Then, we show that when d is small compared to n and the l

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A Survey on Computational Pathology Foundation Models: Datasets, Adaptation Strategies, and Evaluation Tasks

arXiv

引用

arXiv 2025年

作者： Li, Dong Wan, Guihong Wu, Xintao Wu, Xinyu Nirmal, Ajit J. Lian, Christine G. Sorger, Peter K. Semenov, Yevgeniy R. Zhao, Chen Department of Computer Science Baylor University TX United States Department of Dermatology Massachusetts General Hospital Harvard Medical School MA United States Laboratory of Systems Pharmacology Harvard Medical School MA United States Department of Electrical Engineering and Computer Science University of Arkansas AR United States Department of Dermatology Brigham and Women’s Hospital Harvard Medical School MA United States Department of Pathology Brigham and Women’s Hospital Harvard Medical School MA United States

Computational pathology foundation models (CPathFMs) have emerged as a powerful approach for analyzing histopathological data, leveraging self-supervised learning to extract robust feature representations from unlabeled whole-slide images. These models, categorized into uni-modal and multi-modal frameworks, have demonstrated promise in automating complex pathology tasks such as segmentation, classification, and biomarker discovery. However, the development of CPathFMs presents significant challenges, such as limited data accessibility, high variability across datasets, the necessity for domain-specific adaptation, and the lack of standardized evaluation benchmarks. This survey provides a comprehensive review of CPathFMs in computational pathology, focusing on datasets, adaptation strategies, and evaluation tasks. We analyze key techniques, such as contrastive learning and multi-modal integration, and highlight existing gaps in current research. Finally, we explore future directions from four perspectives for advancing CPathFMs. This survey serves as a valuable resource for researchers, clinicians, and AI practitioners, guiding the advancement of CPathFMs toward robust and clinically applicable AI-driven pathology solutions. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Knowledge-Driven Deep Learning for Intelligent Wireless Network Optimization in 6G

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Sun, Ruijin Cheng, Nan Li, Changle Quan, Wei Zhou, Haibo Wang, Ying Zhang, Wei Shen, Xuemin Xidian University State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Xi’an 710071 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing 100044 China Nanjing University School of Electronic Science and Engineering Nanjing 210023 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing 100876 China University of New South Wales School of Electrical Engineering and Telecommunications Sydney 2052 Australia University of Waterloo Department of Electrical and Computer Engineering Waterloo N2L 3G1 ON Canada

The sixth generation (6G) wireless networks are envisioned to feature wide-area coverage, diversified full-scenario services, massive connections and dynamic heterogeneity, resulting in large-scale and complex network optimization problems. Traditional model-based methods, while effective in simple scenarios with precise mathematical models, struggle with high computational intensity and long processing times in the realistic and intricate applications of 6G. Pure data-driven deep learning (DL) methods offer powerful approximation capabilities and fast online inference but are hindered by insufficient datasets and poor interpretability. To address these issues, knowledge-driven DL integrates domain knowledge into neural networks, combining the strengths of both model-based and data-driven approaches. This survey systematically reviews knowledge-driven DL in wireless networks from a novel perspective of the knowledge integration approach. It provides a comprehensive definition of domain knowledge in wireless networks and clarifies the types of knowledge and their representations that can be integrated into neural networks. Furthermore, a leading taxonomy of knowledge integration approaches in wireless networks is proposed, encompassing the integration of domain knowledge into neural network model selection, neural network model customization, knowledge and data fusion architecture construction, loss function design, and hyperparameter configuration. Based on this taxonomy, literature on knowledge-driven resource allocation and signal processing is thoroughly reviewed. This survey aims to provide an insightful guideline for effectively incorporating domain knowledge into neural networks in the field of wireless communications, ultimately advancing efficient and reliable intelligent 6G networks. © 1998-2012 IEEE.

关键词： Domain knowledge intelligent wireless networks knowledge-driven DL neural networks

来源：评论

学校读者我要写书评

暂无评论

Green Routing Game: Strategic Logistical Planning using Mixed Fleets of ICEVs and EVs

arXiv

引用

arXiv 2022年

作者： Sasahara, Hampei Dán, György Amin, Saurabh Sandberg, Henrik The Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo152-8552 Japan The Division of Network and Systems Engineering School of Electrical Engineering and Computer Science Kth Royal Institute of Technology StockholmSE-100 44 Sweden The Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Division of Decision and Control Systems School of Electrical Engineering and Computer Science Kth Royal Institute of Technology StockholmSE-100 44 Sweden

This paper introduces a "green" routing game between multiple logistic operators (players), each owning a mixed fleet of internal combustion engine vehicle (ICEV) and electric vehicle (EV) trucks. Each player faces the cost of delayed delivery (due to charging requirements of EVs) and a pollution cost levied on the ICEVs. This cost structure models: 1) limited battery capacity of EVs and their charging requirement;2) shared nature of charging facilities;3) pollution cost levied by regulatory agency on the use of ICEVs. We characterize Nash equilibria of this game and derive a condition for its uniqueness. We also use the gradient projection method to compute this equilibrium in a distributed manner. Our equilibrium analysis is useful to analyze the trade-off faced by players in incurring higher delay due to congestion at charging locations when the share of EVs increases versus a higher pollution cost when the share of ICEVs increases. A numerical example suggests that to increase marginal pollution cost can dramatically reduce inefficiency of equilibria. © 2022, CC BY-NC-ND.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Massively Digitized Power Grid: Opportunities and Challenges of Use-inspired AI

arXiv

引用

arXiv 2022年

作者： Xie, Le Zheng, Xiangtian Sun, Yannan Huang, Tong Bruton, Tony The Department of Electrical and Computer Engineering Texas A&M University United States The Laboratory for Information and Decision Systems Massachusetts Institute of Technology United States Oncor Electric Delivery United States

This article presents a use-inspired perspective of the opportunities and challenges in a massively digitized power grid. It argues that the intricate interplay of data availability, computing capability, and artificial intelligence (AI) algorithm development are the three key factors driving the adoption of digitized solutions in the power grid. The impact of these three factors on critical functions of power system operation and planning practices are reviewed and illustrated with industrial practice case studies. Open challenges and research opportunities for data, computing, and AI algorithms are articulated within the context of the power industry's tremendous decarbonization efforts. © 2022, CC BY.

关键词： Electric power transmission networks

来源：评论

学校读者我要写书评

暂无评论

Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimization

arXiv

引用

arXiv 2024年

作者： Daunas, Francisco Esnaola, Iñaki Perlaza, Samir M. Vincent Poor, H. The Department of Automatic Control & Systems Engineering The University of Sheffield SheffieldS1 3JD United Kingdom INRIA Centre Inria d'Université Côte d'Azur Sophia Antipolis06902 France The Department of Automatic Control and Systems Engineering The University of Sheffield SheffieldS1 3JD United Kingdom The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States The GAATI Mathematics Laboratory University of French Polynesia Fa'a'ā98702 French Polynesia

The effect of relative entropy asymmetry is analyzed in the context of empirical risk minimization (ERM) with relative entropy regularization (ERM-RER). Two regularizations are considered: (a) the relative entropy of the measure to be optimized with respect to a reference measure (Type-I ERM-RER);or (b) the relative entropy of the reference measure with respect to the measure to be optimized (Type-II ERM-RER). The main result is the characterization of the solution to the Type-II ERM-RER problem and its key properties. By comparing the well-understood Type-I ERM-RER with Type-II ERM-RER, the effects of entropy asymmetry are highlighted. The analysis shows that in both cases, regularization by relative entropy forces the solution's support to collapse into the support of the reference measure, introducing a strong inductive bias that can overshadow the evidence provided by the training data. Finally, it is shown that Type-II regularization is equivalent to Type-I regularization with an appropriate transformation of the empirical risk function. © 2024, CC BY.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective Community-Hierarchy-Based Mutual Voting Approach for Influence Maximization in Complex Networks

arXiv

引用

arXiv 2024年

作者： Liu, Yi Tang, Xiaoan Pedrycz, Witold Zhang, Qiang The Key Laboratory of Process Optimization and Intelligent Decision-making Ministry of Education The School of Management Hefei University of Technology Hefei Box 270 Anhui Hefei230009 China The Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada The Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer Istanbul Turkey

Various types of promising techniques have come into being for influence maximization whose aim is to identify influential nodes in complex networks. In essence, real-world applications usually have high requirements on the balance between time complexity and accuracy of influential nodes identification. To address the challenges of imperfect node influence measurement and inefficient seed nodes selection mechanism in such class of foregoing techniques, this article proposes a novel approach called Cost-Effective Community-Hierarchy-Based Mutual Voting for influence maximization in complex networks. First, we develop a method for measuring the importance of different nodes in networks based on an original concept of Dual-Scale Community-Hierarchy Information that synthesizes both hierarchy structural information and community structural information of nodes. The community structural information contained in the nodes is measured by a new notion of Hierarchical-Community Entropy. Second, we develop a method named Cost-Effective Mutual-Influence-based Voting for seed nodes selection. Hereinto, a low-computational-cost mutual voting mechanism and an updating strategy called Lazy Score Updating Strategy are newly constructed for optimizing the selecting of seed nodes. Third, we develop a balance index to evaluate the performance of different methods in striking the tradeoff between time complexity and the accuracy of influential nodes identification. Finally, we demonstrate the approach performance over ten public datasets. The extensive experiments show that the proposed approach outperforms 16 state-of-the-art techniques on the balance between time complexity and accuracy of influential nodes identification. Compared with the method with the second highest value of the balance index, our approach can be improved by at most 9.29%. Copyright © 2024, The Authors. All rights reserved.

关键词： Expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Integrated Photonic-Electronic Memristors

Integrated Photonic-Electronic Memristors

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Alexandros Emboras Kevin Portner Christoph Weilenmann Till Zellweger Mila Lewerenz Bojun Cheng Elias Passerini Alessandro Alabastri Ping Ma Juerg Leuthold Mathieu Luisier Integrated Systems Laboratory (IIS) ETH Zurich Zurich Switzerland Institute of Electromagnetic Fields (IEF) ETH Zurich Switzerland Department of Electrical and Computer Engineering Rice University Houston Texas USA

We integrate memristors in a silicon photonic/plasmonic platform and demonstrate modulators, photodetectors and electronic devices complemented with memory effect. The demonstrated memristors could be the key photonic... 详细信息

ISBN: (数字)9781957171050

ISBN: (纸本)9781665466660

关键词： Integrated optics Neuromorphics Memristors Modulation Electro-optic modulators Silicon Photodetectors

来源：评论

学校读者我要写书评

暂无评论

A 915MHz $19\mu \mathrm{W}$ Blocker-Enhanced Wake-Up Receiver with Frequency-Hopping Two-Tone Modulation Achieving 53dB Tolerance to In-Band Interference

A 915MHz $19\mu \mathrm{W}$ Blocker-Enhanced Wake-Up Receive...

引用

IEEE Symposium on Radio Frequency Integrated Circuits (RFIC)

作者： Heyu Ren Dawei Ye Binbin Chen Xu Jin Wenjun Gong Rongjin Xu C.-J. Richard Shi State Key Laboratory of ASIC and System Fudan University China Institute of Brain-inspired Circuits and Systems (iBiCAS) Fudan University China Department of Electrical and Computer Engineering University of Washington USA

ISBN: (数字)9781665496117

ISBN: (纸本)9781665496124

A 915MHz ultra-low-power blocker-enhanced wake- up receiver (BE-WuRx) is presented in a 65nm CMOS process. Employing the proposed frequency-hopping two-tone modulation (FH-TTM), the BE-WuRx can dynamically convert the in-band blocker power to data power, and achieves a −63.6dBm sensitivity without blocker and a −90dBm enhanced sensitivity with a −25dBm CW interferer, while just consuming $\mathbf{19}\mathbf{\mu}\mathbf{W}$ . With the −63.6dBm sensitivity, the BE-WuRx performs 53dB tolerance to the in-band blocker, exhibiting 14dB improvement compared to the case that FH- TTM is off. The wake-up latency is 6.4ms for a quiet channel and 6.4 to 64ms for a congested channel.

关键词： Sensitivity Frequency modulation Amplitude shift keying Receivers Interference Frequency conversion CMOS process

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：