检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Abdar, Moloud Pourpanah, Farhad Hussain, Sadiq Rezazadegan, Dana Liu, Li Ghavamzadeh, Mohammad Fieguth, Paul Cao, Xiaochun Khosravi, Abbas Rajendra Acharya, U. Makarenkov, Vladimir Nahavandi, Saeid Deakin University Australia College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Shenzhen518060 China Dibrugarh University Dibrugarh India Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia Center for Machine Vision and Signal Analysis University of Oulu Oulu Finland Google research United States Department of Systems Design Engineering University of Waterloo Waterloo Canada State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Electronics and Computer Engineering Ngee Ann Polytechnic Clementi Singapore Department of Computer Science University of Quebec in Montreal MontrealQC Canada

—Uncertainty quantification (UQ) plays a pivotal role in the reduction of uncertainties during both optimization and decision making, applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two of the most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlight the fundamental research challenges and directions associated with the UQ field. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

No One Left Behind: Real-World Federated Class-Incremental Learning

arXiv

引用

arXiv 2023年

作者： Dong, Jiahua Li, Hongliu Cong, Yang Sun, Gan Zhang, Yulun Van Gool, Luc The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China The University of Chinese Academy of Sciences Beijing100049 China The Department of Civil and Environmental Engineering Hong Kong Polytechnic University Hong Kong The College of Automation Science and Engineering South China University of Technology Guangzhou510640 China The Computer Vision Lab ETH Zürich Zürich8092 Switzerland

Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://***/JiahuaDong/LGA. 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

Automatic generation of modules of object categorization for autonomous mobile robots

引用

AIP Conference Proceedings 2013年第1期1558卷

作者： Anna Gorbenko Ural Federal University Department of Intelligent Systems and Robotics Mathematics and Computer Science Institute Lenin st. 51 620083 Ekaterinburg Russia

Many robotic tasks require advanced systems of visual sensing. Robotic systems of visual sensing must be able to solve a number of different complex problems of visual data analysis. Object categorization is one of such problems. In this paper, we propose an approach to automatic generation of computationally effective modules of object categorization for autonomous mobile robots. This approach is based on the consideration of the stack cover problem. In particular, it is assumed that the robot is able to perform an initial inspection of the environment. After such inspection, the robot needs to solve the stack cover problem by using a supercomputer. A solution of the stack cover problem allows the robot to obtain a template for computationally effective scheduling of object categorization. Also, we consider an efficient approach to solve the stack cover problem. In particular, we consider an explicit reduction from the decision version of the stack cover problem to the satisfiability problem. For different satisfiability algorithms, the results of computational experiments are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Medical Image Segmentation with High-Fidelity Prototypes

arXiv

引用

arXiv 2024年

作者： Tang, Song Yan, Shaxu Qi, Xiaozhi Gao, Jianxin Ye, Mao Zhang, Jianwei Zhu, Xiatian IMI Group School of Health Sciences and Engineering University of Shanghai for Science and Technology Shanghai China TAMS Group Department of Informatics Universität Hamburg Hamburg Germany School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Surrey Institute for People-Centred Artificial Intelligence Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China

Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are limited to the imaging scenarios with considerably distinct objects and not highly complex background, e.g., natural images. This makes such models suboptimal for medical imaging with both conditions invalid. To address this problem, we propose a novel Detail Self-refined Prototype Network (DSPNet) to constructing high-fidelity prototypes representing the object foreground and the background more comprehensively. Specifically, to construct global semantics while maintaining the captured detail semantics, we learn the foreground prototypes by modelling the multi-modal structures with clustering and then fusing each in a channel-wise manner. Considering that the background often has no apparent semantic relation in the spatial dimensions, we integrate channel-specific structural information under sparse channel-aware regulation. Extensive experiments on three challenging medical image benchmarks show the superiority of DSPNet over previous state-of-the-art methods. The code and data are available at https://***/tntek/DSPNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Flat Rotman lens for 5G beamforming antenna

Flat Rotman lens for 5G beamforming antenna

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Muhammad Kamran Khattak Changhyung Lee Dajung Han Sungtek Kahng Department of Information Technologies Università degli Studi di Milano Doctoral School of Computer Science Crema Italy Doctoral School of Applied Informatics and Applied Mathematics Obuda University Budapest Hungary Antal Bejczy Center for Intelligent Robotics (ABC iRob) Obuda University Budapest Hungary Institute of Mechatronics and Vehicle Engineering Obuda University Budapest Hungary Department of Mathematics and Informatics J. Selye University Komarno Slovakia Department of Information Technologies Università degli Studi di Milano Crema Italy

ISBN: (纸本)9781467372381

In this paper, a planar Rotman lens featured as beamforming and multiple beams is presented, aimed at the potential use for 5G communication. The feeding network and the radiating patches are made as a single layer Taconic-microstrip structure for a 24-GHz area operation for low cost and practicality. The beamforming characteristics are verified by the full-wave simulation which is validated by the fabrication and measurement.

关键词： Lenses Ports (computers) Feeds Array signal processing 5G mobile communication Microstrip

来源：评论

学校读者我要写书评

暂无评论

Applications of Evolutionary Computation 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Cecilia Chio Alexandros Agapitos Stefano Cagnoni Carlos Cotta Francisco Fernández Vega Gianni A. Caro Rolf Drechsler Anikó Ekárt Anna I. Esparcia-Alcázar Muddassar Farooq William B. Langdon Juan J. Merelo-Guervós Mike Preuss Hendrik Richter Sara Silva Anabela Simões Giovanni Squillero Ernesto Tarantino Andrea G. B. Tettamanzi Julian Togelius Neil Urquhart A. Şima Uyar Georgios N. Yannakakis

ISBN: (数字)9783642291784

ISBN: (纸本)9783642291777

This book constitutes the refereed proceedings of the International Conference on the Applications of Evolutionary Computation, EvoApplications 2012, held in Málaga, Spain, in April 2012, colocated with the Evo* 2012 events EuroGP, EvoCOP, EvoBIO, and EvoMUSART. The 54 revised full papers presented were carefully reviewed and selected from 90 submissions. EvoApplications 2012 consisted of the following 11 tracks: EvoCOMNET (nature-inspired techniques for telecommunication networks and other parrallel and distributed systems), EvoCOMPLEX (algorithms and complex systems), EvoFIN (evolutionary and natural computation in finance and economics), EvoGAMES (bio-inspired algorithms in games), EvoHOT (bio-inspired heuristics for design automation), EvoIASP (evolutionary computation in image analysis and signal processing), EvoNUM (bio-inspired algorithms for continuous parameter optimization), EvoPAR (parallel implementation of evolutionary algorithms), EvoRISK (computational intelligence for risk management, security and defense applications), EvoSTIM (nature-inspired techniques in scheduling, planning, and timetabling), and EvoSTOC (evolutionary algorithms in stochastic and dynamic environments).

关键词： Computation by Abstract Devices Programming Techniques computer Communication Networks Math Applications in computer science Image Processing and computer vision Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2021 depth guided image relighting challenge

arXiv

引用

arXiv 2021年

作者： Helou, Majed El Zhou, Ruofan Süsstrunk, Sabine Timofte, Radu Suin, Maitreya Rajagopalan, A.N. Wang, Yuanzhi Lu, Tao Zhang, Yanduo Wu, Yuntao Yang, Hao-Hsiang Chen, Wei-Ting Kuo, Sy-Yen Luo, Hao-Lun Zhang, Zhiguang Luo, Zhipeng He, Jianye Zhu, Zuo-Liang Li, Zhen Qiu, Jia-Xiong Kuang, Zeng-Sheng Lu, Cheng-Ze Cheng, Ming-Ming Shao, Xiu-Li Li, Chenghua Ding, Bosong Qian, Wanli Li, Fangya Li, Fu Deng, Ruifeng Lin, Tianwei Liu, Songhua Li, Xin He, Dongliang Yazdani, Amirsaeed Guo, Tiantong Monga, Vishal Nsampi, Ntumba Elie Hu, Zhongyun Wang, Qing Nathan, Sabari Kansal, Priya Zhao, Tongtong Zhao, Shanshan EPFL Switzerland ETH Zürich Switzerland ASUS Intelligent Cloud Services ASUSTeK Computer Inc Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Institute of Automation Chinese Academy of Sciences China Couger Inc Co. Ltd China United States Indian Institute of Technology Madras India Nankai University China Computer Vision and Computational Photography Group School of Computer science Northwestern Polytechnical University China Dalian Maritime University China China Everbright Bank China Baidu Inc China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology China

Image relighting is attracting increasing interest due to its various applications. From a research perspective, image relighting can be exploited to conduct both image normalization for domain adaptation, and also for data augmentation. It also has multiple direct uses for photo montage and aesthetic enhancement. In this paper, we review the NTIRE 2021 depth guided image relighting challenge. We rely on the VIDIT dataset for each of our two challenge tracks, including depth information. The first track is on one-to-one relighting where the goal is to transform the illumination setup of an input image (color temperature and light source position) to the target illumination setup. In the second track, the any-to-any relighting challenge, the objective is to transform the illumination settings of the input image to match those of another guide image, similar to style transfer. In both tracks, participants were given depth information about the captured scenes. We had nearly 250 registered participants, leading to 18 confirmed team submissions in the final competition stage. The competitions, methods, and final results are presented in this paper. Copyright © 2021, The Authors. All rights reserved.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

The discrete minimum constraint removal motion planning problem

引用

AIP Conference Proceedings 2015年第1期1648卷

作者： Anna Gorbenko Vladimir Popov Ural Federal University Department of Intelligent Systems and Robotics Mathematics and Computer Science Institute Lenin st. 51 620083 Ekaterinburg Russian Federation

Many planning problems for robots are of considerable interest. In this paper, we consider the discrete minimum constraint removal motion planning problem that can be used for a motion planning formulation with explanations for failure. We consider an efficient approach to solve the problem. In particular, we consider an explicit reduction from the decision version of the problem to the satisfiability problem. We present the results of computational experiments for different satisfiability algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fingerprints selection for topological localization

引用

AIP Conference Proceedings 2017年第1期1863卷

作者： Vladimir Popov Ural Federal University Department of Intelligent Systems and Robotics Mathematics and Computer Science Institute Lenin st. 51 620083 Ekaterinburg Russian Federation

Problems of visual navigation are extensively studied in contemporary robotics. In particular, we can mention different problems of visual landmarks selection, the problem of selection of a minimal set of visual landmarks, selection of partially distinguishable guards, the problem of placement of visual landmarks. In this paper, we consider one-dimensional color panoramas. Such panoramas can be used for creating fingerprints. Fingerprints give us unique identifiers for visually distinct locations by recovering statistically significant features. Fingerprints can be used as visual landmarks for the solution of various problems of mobile robot navigation. In this paper, we consider a method for automatic generation of fingerprints. In particular, we consider the bounded Post correspondence problem and applications of the problem to consensus fingerprints and topological localization. We propose an efficient approach to solve the bounded Post correspondence problem. In particular, we use an explicit reduction from the decision version of the problem to the satisfiability problem. We present the results of computational experiments for different satisfiability algorithms. In robotic experiments, we consider the average accuracy of reaching of the target point for different lengths of routes and types of fingerprints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task sequencing for autonomous robotic vacuum cleaners

引用

AIP Conference Proceedings 2017年第1期1863卷

Various planning problems for robotic systems are of considerable interest. One of such problems is the problem of task sequencing. In this paper, we consider the problem of task sequencing for autonomous vacuum floor cleaning robots. We consider a graph model for the problem. We propose an efficient approach to solve the problem. In particular, we use an explicit reduction from the decision version of the problem to the satisfiability problem. We present the results of computational experiments for different satisfiability algorithms.

关键词：

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：