检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hu, Jinhui Chen, Guo Li, Huaqing Cheng, Huqiang Guo, Xiaoyu Huang, Tingwen School of Automation Central South University Changsha410083 China Department of Biomedical Engineering City University of Hong Kong Kowloon Hong Kong School of Electrical Engineering and Telecommunications University of New South Wales SydneyNSW2052 Australia Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Privacy leakage and Byzantine failures are two adverse factors to the intelligent decision-making process of multiagent systems (MASs). Considering an unsafe MAS with these two issues, this paper targets the resolution of a class of nonconvex optimization problems under the Polyak-Lojasiewicz (P-L) condition. To address this problem, we first identify and construct the unsafe MAS model. Under this kind of unfavorable MASs, we mask the local gradients with Gaussian noises and adopt a resilient aggregation method self-centered clipping (SCC) to design a differentially private (DP) decentralized Byzantine-resilient algorithm, namely DP-SCC-PL, which simultaneously achieves differential privacy and Byzantine resilience. The convergence analysis of DP-SCC-PL is challenging since the convergence error can be contributed jointly by privacy-preserving and Byzantine-resilient mechanisms, as well as the nonconvex relaxation, which is addressed via seeking the contraction relationships among the disagreement measure of reliable agents before and after SCC aggregation, together with the optimal gap. Theoretical results reveal that DP-SCC-PL achieves consensus among all reliable agents and sublinear (inexact) convergence with well-designed step-sizes. It has also been proved that if there are no privacy issues and Byzantine agents, then the asymptotic exact convergence can be recovered. Numerical experiments verify the utility, resilience, and differential privacy of DP-SCC-PL by tackling a nonconvex optimization problem satisfying the P-L condition under various Byzantine attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

AIM 2020 Challenge on Image Extreme Inpainting 16th

AIM 2020 Challenge on Image Extreme Inpainting

引用

Workshops held at the 16th European Conference on computer Vision, ECCV 2020

作者： Ntavelis, Evangelos Romero, Andrés Bigdeli, Siavash Timofte, Radu Hui, Zheng Wang, Xiumei Gao, Xinbo Shin, Chajin Kim, Taeoh Son, Hanbin Lee, Sangyoun Li, Chao Li, Fu He, Dongliang Wen, Shilei Ding, Errui Bai, Mengmeng Li, Shuchen Zeng, Yu Lin, Zhe Yang, Jimei Zhang, Jianming Shechtman, Eli Lu, Huchuan Zeng, Weijian Ni, Haopeng Cai, Yiyang Li, Chenghua Xu, Dejia Wu, Haoning Han, Yu Nadim, Uddin S. M. Jang, Hae Woong Ahmed, Soikat Hasan Yoon, Jungmin Jung, Yong Ju Li, Chu-Tak Liu, Zhi-Song Wang, Li-Wen Siu, Wan-Chi Lun, Daniel P. K. Suin, Maitreya Purohit, Kuldeep Rajagopalan, A.N. Narang, Pratik Mandal, Murari Chauhan, Pranjal Singh Computer Vision Lab ETH Zürich Zürich Switzerland CSEM Neuchâtel Switzerland School of Electronic Engineering Xidian University Xi’an China Image and Video Pattern Recognition Laboratory School of Electrical and Electronic Engineering Yonsei University Seoul Korea Republic of Baidu Inc. Beijing China Beijing China Dalian University of Technology Dalian China Adobe San Jose United States Rensselaer Polytechnic Institute Troy United States Peking University Beijing China Lab Gachon University Seongnam Korea Republic of Centre for Multimedia Signal Processing Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong China Indian Institute of Technology Madras Chennai India BITS Pilani Pilani India MNIT Jaipur Jaipur India

ISBN: (纸本)9783030670696

This paper reviews the AIM 2020 challenge on extreme image inpainting. This report focuses on proposed solutions and results for two different tracks on extreme image inpainting: classical image inpainting and semantically guided image inpainting. The goal of track 1 is to inpaint large part of the image with no supervision. Similarly, the goal of track 2 is to inpaint the image by having access to the entire semantic segmentation map of the input. The challenge had 88 and 74 participants, respectively. 11 and 6 teams competed in the final phase of the challenge, respectively. This report gauges current solutions and set a benchmark for future extreme image inpainting methods. © 2020, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Quantitative assessment of the effects of resource optimization and ICU admission policy on COVID-19 mortalities

引用

Physical Review Research 2022年第3期4卷 033209-033209页

作者： Lang Zeng Ying-Qi Zeng Ming Tang Ying Liu Zonghua Liu Ying-Cheng Lai School of Physics and Electronic Science East China Normal University Shanghai 200241 China School of Communication and Electronic Engineering East China Normal University Shanghai 200241 China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai 200241 China School of Computer Science Southwest Petroleum University Chengdu 610500 People's Republic of China School of Electrical Computer and Energy Engineering Arizona State University Tempe Arizona 85287 USA Department of Physics Arizona State University Tempe Arizona 85287 USA

It is evident that increasing the intensive-care-unit (ICU) capacity and giving priority to admitting and treating patients will reduce the number of COVID-19 deaths, but the quantitative assessment of these measures has remained inadequate. We develop a comprehensive, non-Markovian state transition model, which is validated through the accurate prediction of the daily death toll for two epicenters: Wuhan, China and Lombardy, Italy. The model enables prediction of COVID-19 deaths in various scenarios. For example, if appropriate treatment priorities had been used, the death toll in Wuhan and Lombardy would have been reduced by about 10% and 7%, respectively. The strategy depends on the epidemic scale and is more effective in countries with a younger population structure. Analyses of data from China, South Korea, Italy, and Spain suggest that countries with less per capita ICU medical resources should implement this strategy in the early stage of the pandemic to reduce mortalities. We emphasize that the results of this paper should be interpreted purely from a scientific and a quantitative-analysis point of view. No ethical implications are intended and meaningful.

关键词： Complex systems

来源：评论

学校读者我要写书评

暂无评论

Elevation interferometric STAP using a thinned planar array

Elevation interferometric STAP using a thinned planar array

引用

IEEE National Conference on Radar

作者： T.B. Hale M.A. Temple J.F. Raquet M.E. Oxley M.C. Wicks Dept of Electrical and Computer Engineering (AFIT/ENG) Air Force Institute of Technology OH Dept of Mathematics and Statistics (AFIT/ENC) Air Force Institute of Technology OH Department of Mathematics and Statistics (AFIT/ENC) Air Force Institute of Technology OH USA Sensors Directorate Radar Signal Processing Branch (AFRL/SNRT) Air Force Research Laboratory Rome NY

ISBN: (纸本)078037357X

The research applies space-time adaptive processing (STAP) techniques to a pseudo-circular array generated by selectively thinning a rectangular array. A hybrid approach incorporating elevation interferometry and STAP techniques is used. Results show the thinned 16-element pseudo-circular array offers significant detection performance improvement over the baseline factored time-space (FTS) technique operating on a linear array, e.g., an 8-element horizontal linear array. Results are demonstrated for cases with and without range ambiguous clutter. This performance level is achieved using a factor of M less sample support than required for full adaptivity where M represents the number of pulses within a coherent processing interval.

关键词： Planar arrays Sensor arrays Clutter Force sensors Adaptive arrays Degradation Filtering Military computing Mathematics Statistics

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning

arXiv

引用

arXiv 2024年

作者： Yang, Kuo Li, Duo Hu, Menghan Zhai, Guangtao Yang, Xiaokang Zhang, Xiao-Ping The Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China The Kargobot of DiDi Shanghai201210 China The Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China Tsinghua Berkeley Shenzhen Institute Shenzhen China The Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University ONM5B 2K3 Canada

For semi-supervised learning with imbalance classes, the long-tailed distribution of data will increase the model prediction bias toward dominant classes, undermining performance on less frequent classes. Existing methods also face challenges in ensuring the selection of sufficiently reliable pseudo-labels for model training and there is a lack of mechanisms to adjust the selection of more reliable pseudo-labels based on different training stages. To mitigate this issue, we introduce uncertainty into the modeling process for pseudo-label sampling, taking into account that the model performance on the tailed classes varies over different training stages. For example, at the early stage of model training, the limited predictive accuracy of model results in a higher rate of uncertain pseudo-labels. To counter this, we propose an Uncertainty-Aware Dynamic Threshold Selection (UDTS) approach. This approach allows the model to perceive the uncertainty of pseudo-labels at different training stages, thereby adaptively adjusting the selection thresholds for different classes. Compared to other methods such as the baseline method FixMatch, UDTS achieves an increase in accuracy of at least approximately 5.26%, 1.75%, 9.96%, and 1.28% on the natural scene image datasets CIFAR10-LT, CIFAR100-LT, STL-10-LT, and the medical image dataset TissueMNIST, respectively. The source code of UDTS is publicly available at: https://***/yangk/UDTS. Copyright © 2024, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Learning with Prior Knowledge

arXiv

引用

arXiv 2024年

作者： Jiang, Wenhao Li, Duo Hu, Menghan Zhai, Guangtao Yang, Xiaokang Zhang, Xiao-Ping Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China Kargobot of DiDi Shanghai201210 China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China Tsinghua Berkeley Shenzhen Institute Shenzhen China Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University ONM5B 2K3 Canada

To tackle the issues of catastrophic forgetting and overfitting in few-shot class-incremental learning (FSCIL), previous work has primarily concentrated on preserving the memory of old knowledge during the incremental phase. The role of pre-trained model in shaping the effectiveness of incremental learning is frequently underestimated in these studies. Therefore, to enhance the generalization ability of the pre-trained model, we propose Learning with Prior Knowledge (LwPK) by introducing nearly free prior knowledge from a few unlabeled data of subsequent incremental classes. We cluster unlabeled incremental class samples to produce pseudo-labels, then jointly train these with labeled base class samples, effectively allocating embedding space for both old and new class data. Experimental results indicate that LwPK effectively enhances the model resilience against catastrophic forgetting, with theoretical analysis based on empirical risk minimization and class distance measurement corroborating its operational principles. The source code of LwPK is publicly available at: https://***/StevenJ308/LwPK. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

IMART software for correction of motion artifacts in images collected in intravital microscopy

引用

Intravital 2014年第1期3卷 e28210页

作者： Kenneth W Dunn Kevin S Lorenz Paul Salama Edward J Delp Division of Nephrology School of Medicine Indiana University Indianapolis IN USA. Video and Image Processing Laboratory School of Electrical and Computer Engineering Purdue University West Lafayette IN USA. Department of Electrical and Computer Engineering

Intravital microscopy is a uniquely powerful tool, providing the ability to characterize cell and organ physiology in the natural context of the intact, living animal. With the recent development of high-resolution microscopy techniques such as confocal and multiphoton microscopy, intravital microscopy can now characterize structures at subcellular resolution and capture events at sub-second temporal resolution. However, realizing the potential for high resolution requires remarkable stability in the tissue. Whereas the rigid structure of the skull facilitates high-resolution imaging of the brain, organs of the viscera are free to move with respiration and heartbeat, requiring additional apparatus for immobilization. In our experience, these methods are variably effective, so that many studies are compromised by residual motion artifacts. Here we demonstrate the use of IMART, a software tool for removing motion artifacts from intravital microscopy images collected in time series or in three dimensions.

关键词： fluorescence microscopy image analysis image processing image registration in vivo imaging intravital microscopy motion artifact multiphoton microscopy

来源：评论

学校读者我要写书评

暂无评论

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

arXiv

引用

arXiv 2022年

作者： Wang, Muhan Zhang, Zhe Wang, Yue Gao, Silin Qiu, Xiaolan Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Electrical and Computer Engineering Department George Mason University FairfaxVA22030 United States

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations. In recent years, compressed sensing (CS) technique has been introduced into TomoSAR considering for its super-resolution ability with limited samples. Whereas, the CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity and complex parameter fine-tuning. Among the different CS algorithms, iterative soft-thresholding algorithm (ISTA) is widely used as a robust reconstruction approach, however, the parameters in the ISTA algorithm are manually chosen, which usually requires a time-consuming fine-tuning process to achieve the best performance. Aiming at efficient TomoSAR imaging, a novel sparse unfolding network named analytic learned ISTA (ALISTA) is proposed towards the TomoSAR imaging problem in this paper, and the key parameters of ISTA are learned from training data via deep learning to avoid complex parameter fine-tuning and significantly relieves the training burden. In addition, experiments verify that it is feasible to use traditional CS algorithms as training labels, which provides a tangible supervised training method to achieve better 3D reconstruction performance even in the absence of labeled data in real applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Artificial Neural Network to Model Characteristic Fluctuation of Multi-Channel Gate-All-Around Silicon Nanosheet and Nanofin MOSFETs Induced by Random Nanosized Metal Grains

Application of Deep Artificial Neural Network to Model Chara...

引用

IEEE Electron Devices Technology and Manufacturing Conference (EDTM)

作者： Sagarika Dash Yiming Li Wen-Li Sung Parallel and Scientific Computing Laboratory National Yang-Ming Chiao Tung University Hsinchu Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang-Ming Chiao Tung University Hsinchu Taiwan Institute of Communications Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Institute of Biomedical Engineering National Yang-Ming Chiao Tung University Hsinchu Taiwan Center for mm Wave Smart Radar System and Technologies National Yang-Ming Chiao Tung University Hsinchu Taiwan

In this work, we propose a deep artificial neural network (D-ANN) to estimate the work function fluctuation (WKF) on 4-channel stacked gate-all-around (GAA) silicon (Si) nanosheet (NS) and nanofin (NF) MOSFET devices for the first time. The 2-layered simple deep model can well predict the transfer characteristics for both NS/NF FET with a large number of (128) input features, utilizing considerably lesser (1100 samples) data uniformly. The resultant model is evaluated by the $\mathrm{R}^{2}$ score and RMSE to witness its competency and the average error is $< 4\%$ . We do also discuss the circuit simulation possibility by applying the ANN approach.

关键词： Semiconductor device modeling MOSFET Gallium arsenide Artificial neural networks Predictive models Logic gates Silicon

来源：评论

学校读者我要写书评

暂无评论

GEOAIDA applied to SPOT satellite image interpretation

GEOAIDA applied to SPOT satellite image interpretation

引用

GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas

作者： S. Muller R.Q. Feitosa G.L. Abelha Mota D.P. da Costa V.V. da Silva K. Tanisaki Institute of Communication Theory and Signal Processing University of Hanover Hanover Germany Department of Electrical Engineering Catholic University of Rio de Janeiro Rio de Janeiro Brasil Department of Computer Engineering State University of Rio de Janeiro Rio de Janeiro Brasil Applied Geology Department State University of Rio de Janeiro Rio de Janeiro Brasil Radioecology and Global Change Laboratory and Researcher of Geomatic Program State University of Rio de Janeiro Rio de Janeiro Brasil

This paper investigates the application of a knowledge-based approach, founded on semantic networks, to the automatic land use mapping assisted by low resolution satellite images. Like the visual photo-interpretation, the automatic image interpretation considers scene and sensors knowledge, delivered by an expert photo-interpreter, as well as additional information about the region like the digital elevation model, the position of the emergent rocks, the mapping of the water bodies and the road-network. By this means, the analysis of a scene can be automatically performed, mimicking the reasoning of the photo-interpreter. The implementation of such proposal employed the GEOAIDA [J. Buckner et al., June 2001] system, a flexible environment for image interpretation developed at the University of Hanover, which exploits semantic networks to structure the domain specific knowledge. In the reported experiments, a multispectral SPOT 3 XS image was analysed resulting were evaluated and compared with a manually made reference map of the investigated scene. The automatically obtained results were evaluated and compared with a manually made reference map of the investigated scene. The experimental results demonstrate the potential of a knowledge-based approach for low resolution satellite images interpretation.

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：