检索结果-内蒙古大学图书馆

Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach

学校读者我要写书评

暂无评论

Robust Multi-Exposure Image Fusion: A Structural Patch Decom...

作者： Ma, Kede Li, Hui Yong, Hongwei Wang, Zhou Meng, Deyu Zhang, Lei Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong Department of Computing. Hong Kong Polytechnic University Hong Kong Hong Kong Institute for Information and System Sciences and Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China Inst. for Info. and Syst. Sci. and Min. of Educ. Key Lab. of Intelligent Networks and Netwk. Secty. Xi'an Jiaotong University Xi'an710049 China

We propose a simple yet effective structural patch decomposition approach for multi-exposure image fusion (MEF) that is robust to ghosting effect. We decompose an image patch into three conceptually independent components: signal strength, signal structure, and mean intensity. Upon fusing these three components separately, we reconstruct a desired patch and place it back into the fused image. This novel patch decomposition approach benefits MEF in many aspects. First, as opposed to most pixel-wise MEF methods, the proposed algorithm does not require post-processing steps to improve visual quality or to reduce spatial artifacts. Second, it handles RGB color channels jointly, and thus produces fused images with more vivid color appearance. Third and most importantly, the direction of the signal structure component in the patch vector space provides ideal information for ghost removal. It allows us to reliably and efficiently reject inconsistent object motions with respect to a chosen reference image without performing computationally expensive motion estimation. We compare the proposed algorithm with 12 MEF methods on 21 static scenes and 12 deghosting schemes on 19 dynamic scenes (with camera and object motion). Extensive experimental results demonstrate that the proposed algorithm not only outperforms previous MEF algorithms on static scenes but also consistently produces high quality fused images with little ghosting artifacts for dynamic scenes. Moreover, it maintains a lower computational cost compared with the state-of-The-Art deghosting schemes.11The MATlab.code of the proposed algorithm will be made availab.e online. Preliminary results of Section III-A [1] were presented at the IEEE International Conference on Image Processing, Canada, 2015. © 1992-2012 IEEE.

关键词： Image fusion

lednet: A lightweight encoder-decoder network for real-time semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Yu Zhou, Quan Liu, Jia Xiong, Jian Gao, Guangwei Wu, Xiaofu Latecki, Longin Jan National Engineering Research Center of Communications and Networking Nanjing University of Posts & Telecommunications China Key Lab. of Broadband Wireless Communications and Sensor Network Technology Nanjing University of Posts & Telecommunications China Institute of Advanced Technology Nanjing University of Posts & Telecommunications China Department of Computer and Information Sciences Temple University Philadelphia United States

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation. More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters, and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

Blockchain Assisted Federated Learning over Wireless Channels: Dynamic Resource Allocation and Client Scheduling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Deng, Xiumei Li, Jun Ma, Chuan Wei, Kang Shi, Long Ding, Ming Chen, Wen Poor, H. Vincent The School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China Zhejiang Lab Hangzhou China Nanjing University of Science and Technology Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Data61 CSIRO KensingtonWA6152 Australia The Department of Electronics Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Electrical and Computer Engineering Princeton University NJ08544 United States

The blockchain technology has been extensively studied to enable distributed and tamper-proof data processing in federated learning (FL). Most existing blockchain assisted FL (BFL) frameworks have employed a third-party blockchain network to decentralize the model aggregation process. However, decentralized model aggregation is vulnerable to pooling and collusion attacks from the third-party blockchain network. Driven by this issue, we propose a novel BFL framework that features the integration of training and mining at the client side. To optimize the learning performance of FL, we propose to maximize the long-term time average (LTA) training data size under a constraint of LTA energy consumption. To this end, we formulate a joint optimization problem of training client selection and resource allocation (i.e., the transmit power and computation frequency at the client side), and solve the long-term mixed integer non-linear programming based on a Lyapunov technique. In particular, the proposed dynamic resource allocation and client scheduling (DRACS) algorithm can achieve a trade-off of [O(1/V), O(√V)] to balance the maximization of the LTA training data size and the minimization of the LTA energy consumption with a control parameter V. Our experimental results show that the proposed DRACS algorithm achieves better learning accuracy than benchmark client scheduling strategies with limited time or energy consumption. Copyright © 2021, The Authors. All rights reserved.

关键词： Blockchain

Adaptive genetic algorithm and its application to multi-literal multi-issue competitive e-commerce

学校读者我要写书评

暂无评论

Dianzi Yu Xinxi Xuebao/Journal of Electronics and information Technology 2008年第11期30卷 2613-2616页

作者： Li, Jian Jing, Bo Yang, Yi-Xian Information Security Center State Key Lab. of Network and Switching Technology Beijing University of Posts and Telecommunications Beijing 100876 China Dept. of Computer Technology Beijing Institute of Applied Meteorology Beijing 100029 China

To make the agents negotiate more efficiently in multi-lateral multi-issue negotiation in multi-agent based competitive e-commerce, an agent negotiation model in competitive environment is presented, and the Adaptive Genetic Algorithm (AGA) is applied to the model to enhance the negotiation efficiency. In the experiments, two kinds of genetic algorithms are used to compare with, they are Standard Genetic Algorithm (SGA) and AGA. After 1000 times of experiments for the two kinds of agents to gain the satisfying result, SGA averagely needs negotiation of 183 runs, while the AGA averagely needs only 152 runs. The experiment results show that the AGA can gain the satisfying negotiation result more efficiently than SGA in competitive multi-lateral multi-issue negotiation.

关键词： Electronic commerce

Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Zhuo Zhu, Miaoxi Xia, Xiaobo Shen, Li Yu, Jun Gong, Chen Han, Bo Du, Bo Liu, Tongliang Syndey Ai Centre The University of Sydney Australia National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Jd Explore Academy China Department of Automation University of Science and Technology of China China Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is availab.e, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization

New trust model based on advanced D-S evidence theory for P2P networks

学校读者我要写书评

暂无评论

Dianzi Yu Xinxi Xuebao/Journal of Electronics and information Technology 2008年第6期30卷 1480-1484页

作者： Tian, Chun-Qi Zou, Shi-Hong Wang, Wen-Dong Cheng, Shi-Duan Broadband Network Research Center State Key Lab. of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing 100876 China Department of Computer Science and Technology College of Electronic and Information Engineering Tongji University Shanghai 200092 China

Trust relationship between participants is indispensable to set up in a large-scale distributed P2P file-sharing system. A novel trust model for P2P system based on advanced D-S theory of evidence is proposed in this paper to solve this problem, in which mathematic analysis and some measures are presented to defense against several malicious attacks. The experimental results show that, compared to the current some trust models, the proposed model is more robust on trust security problems and more advanced in successful transaction rate.

关键词： Peer to peer networks

Multi-lab.l Classification with High-rank and High-order lab.l Correlations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Si, Chongjie Jia, Yuheng Wang, Ran Zhang, Min-Ling Feng, Yanghe Qu, Chongxiao The Chien-Shiung Wu College Southeast University Nanjing210096 China The MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China The School of Mathematical Science Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China The College of Systems Engineering National University of Defense Technology China The 52nd Research Institute of China Electronics Technology Group China

Exploiting lab.l correlations is important to multi-lab.l classification. Previous methods capture the high-order lab.l correlations mainly by transforming the lab.l matrix to a latent lab.l space with low-rank matrix factorization. However, the lab.l matrix is generally a full-rank or approximate full-rank matrix, making the low-rank factorization inappropriate. Besides, in the latent space, the lab.l correlations will become implicit. To this end, we propose a simple yet effective method to depict the high-order lab.l correlations explicitly, and at the same time maintain the high-rank of the lab.l matrix. Moreover, we estimate the lab.l correlations and infer model parameters simultaneously via the local geometric structure of the input to achieve mutual enhancement. Comparative studies over twelve benchmark data sets validate the effectiveness of the proposed algorithm in multi-lab.l classification. The exploited high-order lab.l correlations are consistent with common sense empirically. Our code is publicly availab.e at https://***/Chongjie-Si/HOMI. Copyright © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

The design and implementation of network attack and defense platform based on cloud desktop

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2017年第1期887卷

作者： Zining Yan Yunhan Wang Shijiao Shao Boquan Li Embedded System Lab. College of Computer Science and Technology Harbin China Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences Key Laboratory of Network Assessment of Technology Chinese Academy of Sciences Beijing China

This paper discusses the cloud desktop technology, virtualization technology and penetration testing technology used in the network attack and defense training platform, and introduces the design and implementation process of the network attack and defense training platform. This paper focuses on the cloud desktop construction scheme based on B/S structure, and aims to enhance the flexibility and convenience of network attack and defense training platform.

关键词：

25th Annual Computational Neuroscience Meeting CNS-2016, Seogwipo City, South Korea, July 2-7, 2016 Abstracts

学校读者我要写书评

暂无评论

BMC NEUROSCIENCE 2016年第1期17卷 1-112页

作者： [Anonymous] Computational Neurobiology Laboratory The Salk Institute for Biological Studies San Diego USA UNIC CNRS Gif sur Yvette France The European Institute for Theoretical Neuroscience (EITN) Paris France ATR Computational Neuroscience Laboratories Kyoto Japan Krembil Research Institute University Health Network Toronto Canada Department of Physiology University of Toronto Toronto Canada Department of Medicine (Neurology) University of Toronto Toronto Canada Department of Physics University of New Hampshire Durham USA Department of Neurophysiology Nencki Institute of Experimental Biology Warsaw Poland Department of Theory Wigner Research Centre for Physics of the Hungarian Academy of Sciences Budapest Hungary Department of Mathematical Sciences KAIST Daejoen Republic of Korea Department of Mathematics University of Houston Houston USA Department of Biochemistry & Cell Biology and Institute of Biosciences and Bioengineering Rice University Houston USA Department of Biology and Biochemistry University of Houston Houston USA Grupo de Neurocomputación Biológica Dpto. de Ingeniería Informática Escuela Politécnica Superior Universidad Autónoma de Madrid Madrid Spain Department of Biological Sciences University of Southern California Los Angeles USA Center for Neuroscience Korea Institute of Science and Technology Seoul South Korea Department of Neurology Albert Einstein College of Medicine Bronx USA Center for Neuroscience KIST Seoul South Korea Department of Neuroscience University of Science and Technology Daejon South Korea Systems Neuroscience Group QIMR Berghofer Medical Research Institute Herston Australia Department of Psychology Yonsei University Seoul South Korea Department of Psychiatry Kyung Hee University Hospital at Gangdong Seoul South Korea Department of Psychiatry Veterans Administration Boston Healthcare System and Harvard Medical School Brockton USA Department of Electrical and Electronic Engineering The University of Melbourne Parkvil

A1 Functional advantages of cell-type heterogeneity in neural circuits Tatyana O. Sharpee A2 Mesoscopic modeling of propagating waves in visual cortex Alain Destexhe A3 Dynamics and biomarkers of mental disorders Mitsuo Kawato F1 Precise recruitment of spiking output at theta frequencies requires dendritic h-channels in multi-compartment models of oriens-lacunosum/moleculare hippocampal interneurons Vladislav Sekulić, Frances K. Skinner F2 Kernel methods in reconstruction of current sources from extracellular potentials for single cells and the whole brains Daniel K. Wójcik, Chaitanya Chintaluri, Dorottya Cserpán, Zoltán Somogyvári F3 The synchronized periods depend on intracellular transcriptional repression mechanisms in circadian clocks. Jae Kyoung Kim, Zachary P. Kilpatrick, Matthew R. Bennett, Kresimir Josić O1 Assessing irregularity and coordination of spiking-bursting rhythms in central pattern generators Irene Elices, David Arroyo, Rafael Levi, Francisco B. Rodriguez, Pablo Varona O2 Regulation of top-down processing by cortically-projecting parvalbumin positive neurons in basal forebrain Eunjin Hwang, Bowon Kim, Hio-Been Han, Tae Kim, James T. McKenna, Ritchie E. Brown, Robert W. McCarley, Jee Hyun Choi O3 Modeling auditory stream segregation, build-up and bistability James Rankin, Pamela Osborn Popp, John Rinzel O4 Strong competition between tonotopic neural ensembles explains pitch-related dynamics of auditory cortex evoked fields Alejandro Tabas, André Rupp, Emili Balaguer-Ballester O5 A simple model of retinal response to multi-electrode stimulation Matias I. Maturana, David B. Grayden, Shaun L. Cloherty, Tatiana Kameneva, Michael R. Ibbotson, Hamish Meffin O6 Noise correlations in V4 area correlate with behavioral performance in visual discrimination task Veronika Koren, Timm Lochmann, Valentin Dragoi, Klaus Obermayer O7 Input-location dependent gain modulation in cerebellar nucleus neurons Maria Psarrou, Maria Schilstra, Neil Davey, Benjamin Torben-Ni

关键词：