检索结果-内蒙古大学图书馆

18th IEEE Int Symp on parallel and distributed Proc with Applicat (ISPA) / 10th IEEE Int Conf on Big Data and Cloud Comp (BDCloud) / IEEE Int Symp on Social Comp and Networking (SocialCom) / IEEE Int Conf on Sustainable Comp and Commun (SustainCom)

作者： Yuan, Ninghui Liu, Jingyu Wang, Qiong Shen, Li Natl Univ Def Technol Sch Comp Changsha Peoples R China

ISBN: (纸本)9781665414852

As a popular research field of computer vision, super resolution(SR) has received more and more attention in recent years. Although the deep learning methods have achieved good results in SR, there are still some problems. For example, the previous models are often based on single depth mechanism. This means that the SR reconstruction problem of all images is regarded as of equal complexity. And we found that some images have more details and are suitable for recovering in complex models, while other images have less texture information and are suitable for recovering in simple models. At the same time, the size of the training set is too large, which creats a lot of resource overhead. To solve these problems, this paper proposes a new SR framework can be customized according to image features. We choose 3 representative models for testing and in test our framework can reduce the size of the training set by 41.9%. For MSRResNet, we can reduce the training time from 2517 minutes to 2449 minutes. The reconstruction quality of 61% test images has been improved and the average perceptual index has dropped from 5.1912 to 5.155833, at the same time the reconstruction time has been optimized from 85 seconds to 59 seconds. For SRGAN, the training time can be reduced from 1920 minutes to 1812 minutes. The reconstruction quality of 58% test images have been improved and the average perceptual index has dropped from 2.0869 to 2.0509, while the reconstruction time has been optimized from 82 seconds to 46 seconds. For ESRGAN, the training time can be reduced from 4368 minutes to 4249 minutes. The reconstruction quality of 78% test images has been improved and the average perceptual index has dropped from 2.2041 to 2.0535. The reconstruction time has been optimized from 138 seconds to 95 seconds. Our framework can improve the effect of super-resolution models while reducing the resource overhead.

关键词： super-resolution framework random forest

来源：评论

学校读者我要写书评

暂无评论

WBA: A Warping-based Approach to Generating Imperceptible Adversarial Examples

WBA: A Warping-based Approach to Generating Imperceptible Ad...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Chengyao Hua Shigeng Zhang Weiping Wang Zhankai Li Jian Zhang School of Computer Science and Engineering Central South University Changsha China Science and Technology on Parallel and Distributed Processing Laboratory (PDL)

The human can easily recognize the incongruous parts of an image, for example, perturbations unrelated to the image itself, but are poor at spotting the small geometric transformations. However, in terms of the robustness of deep neural networks (DNNs), the ability to properly recognize objects with small geometric transformations is still a challenge. In this work, we investigate the problem from the perspective of adversarial attacks: does the performance of DNNs degrade even when small geometric transformations are applied to images? To this end, we propose a novel adversarial attack method, called WBA, a Warping-Based Adversarial attack method, which does not introduce information independent of the original images but manipulates the existing pixels of the images by elastic warping transformations to generate adversarial examples that are imperceptible to the human eye. At the same time, existing adversarial attacks typically generate adversarial examples by modifying pixels in the spatial domain of the image, the addition of such perturbations introduces extra information unrelated to the image itself and is easily detected by the naked eyes. We demonstrate the effectiveness of WBA by extensive experiments on commonly used datasets, including MNIST, CIFAR10, and imageNet. The results show that WBA can quickly generate adversarial examples with the highest adversarial strength, consumes less time, and can be comparable to optimization-based adversarial attack methods in image perception evaluation metrics such as LPIPS, SSIM, and far more than gradient direction-based iterative methods.

关键词： Measurement Deep learning Privacy image recognition Perturbation methods Neural networks Robustness

来源：评论

学校读者我要写书评

暂无评论

Maximum Mean and Covariance Discrepancy for Unsupervised Domain Adaptation

引用

NEURAL processing LETTERS 2020年第1期51卷 347-366页

作者： Zhang, Wenju Zhang, Xiang Lan, Long Luo, Zhigang Natl Univ Def Technol Sci & Technol Parallel & Distributed Lab Changsha 410073 Peoples R China Natl Univ Def Technol State Key Lab High Performance Comp Changsha 410073 Peoples R China Natl Univ Def Technol Coll Comp Changsha 410073 Peoples R China

A fundamental research topic in domain adaptation is how best to evaluate the distribution discrepancy across domains. The maximum mean discrepancy (MMD) is one of the most commonly used statistical distances in this field. However, information about distributions could be lost when adopting non-characteristic kernels by MMD. To address this issue, we devise a new distribution metric named maximum mean and covariance discrepancy (MMCD) by combining MMD and the proposed maximum covariance discrepancy (MCD). MCD probes the second-order statistics in reproducing kernel Hilbert space, which equips MMCD to capture more information compared to MMD alone. To verify the efficacy of MMCD, an unsupervised learning model based on MMCD abbreviated as McDA was proposed and efficiently optimized to resolve the domain adaptation problem. Experiments on image classification conducted on two benchmark datasets show that McDA outperforms other representative domain adaptation methods, which implies the effectiveness of MMCD in domain adaptation.

关键词： Domain adaptation image classification Dimensionality reduction Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A parallel Drone image Mosaic Method Based on Apache Spark 9th

A Parallel Drone Image Mosaic Method Based on Apache Spark

引用

9th EAI International Conference on Cloud Computing, CloudComp 2019 and the 4th EAI International Conference on Smart Grid and Innovative Frontiers in Telecommunications, SmartGIFT 2019

作者： Wu, Yirui Ge, Lanbo Luo, Yuchi Teng, Deqiang Feng, Jun College of Computer and Information Hohai University Nanjing China

ISBN: (纸本)9783030485122

MapReduce has been widely used to process large-scale data in the past decade. Among the quantity of such cloud computing applications, we pay special attention to distributed mosaic methods based on numerous drone images, which suffers from costly processing time. In this paper, a novel computing framework called Apache Spark is introduced to pursue instant responses for the quantity of drone image mosaic requests. To assure high performance of Spark-based algorithms in a complex cloud computing environment, we specially design a distributed and parallel drone image mosaic method. By modifying to be fit for fast and parallel running, all steps of the proposed mosaic method can be executed in an efficient and parallel manner. We implement the proposed method on Apache Spark platform and apply it to a few self-collected datasets. Experiments indicate that our Spark-based parallel algorithm is of great efficiency and is robust to process low-quality drone aerial images. © 2020, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

3DVSR: 3D EPI volume-based approach for angular and spatial light field image super-resolution

引用

SIGNAL processing 2022年 192卷 108373-108373页

作者： Trung-Hieu Tran Berberich, Jan Simon, Sven Univ Stuttgart Inst Parallel & Distributed Syst D-70569 Stuttgart Germany

Light field (LF) imaging, which captures both spatial and angular information of a scene, is undoubtedly beneficial to numerous applications. Although various techniques have been proposed for LF acquisition, achieving both angularly and spatially high-resolution LF remains a technology challenge. In this paper, a learning-based approach applied to 3D epipolar image (EPI) is proposed to reconstruct high-resolution LF. Through a 2-stage super-resolution framework, the proposed approach effectively addresses various LF super-resolution (SR) problems, i.e., spatial SR, angular SR, and angular-spatial SR. While the first stage provides flexible options to up-sample EPI volume to the desired resolution, the second stage, which consists of a novel EPI volume-based refinement network (EVRN), substantially enhances the quality of the high-resolution EPI volume. An extensive evaluation on 90 challenging synthetic and real-world light field scenes from 7 published datasets shows that the proposed approach outperforms state-of-the-art methods to a large extend for both spatial and angular super-resolution problem, i.e., an average peak signal to noise ratio improvement of more than 2.0 dB, 1.4 dB, and 3.14 dB in spatial SR x2, spatial SR x4, and angular SR respectively. The reconstructed 4D light field demonstrates a balanced performance distribution across all perspective images and presents superior visual quality compared to the previous works. (C) 2021 Elsevier B.V. All rights reserved.

关键词： 3D-EPI volume Angular super-resolution Deep learning Light field Spatial super-resolution

来源：评论

学校读者我要写书评

暂无评论

A novel median-based image impulse noise suppression system using spiking neurons on FPGA

引用

COMPUTER methods IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION 2020年第6期8卷 631-640页

作者： Abhari, Pooya Soleimani Razaghian, Farhad Islamic Azad Univ Dept Elect Engn South Tehran Branch Tehran Iran

The most common impulse noise suppression methods are based on the median filter. They are suitable for low noise densities, but employing a separate noise detection step makes them suitable for higher noise rates. Instead, this may degrade the performance for lower noise. Particularly, the adaptive median noise removal algorithm improves the results for both low and high noise corruption rates. This paper presents a novel noise detection and filtering algorithm that uses leaky integrate and fire spiking neurons which model natural computing of the brain. In the proposed method, at each process of the detection and the filtering, all pixels of an adaptive sliding window are fed to the spiking neurons performing the operations in parallel. As a result, higher processing speed and higher operating frequency are achieved. An FPGA is used to implement the algorithm due to its real-time application and reconfigurable structure. The proposed architecture represents a slight increase in the PSNR values, whereas it consumes less hardware resources compared to the previous works. The design is implemented on Cyclone iv device from Altera family. It includes 3231 LUTs and the maximum operating frequency of 187 MHz is achieved.

关键词： image noise cancellation FPGA implementation salt and pepper noise

来源：评论

学校读者我要写书评

暂无评论

Unified Density-Aware image Dehazing and Object Detection in Real-World Hazy Scenes 15th

Unified Density-Aware Image Dehazing and Object Detection in...

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhang, Zhengxi Zhao, Liang Liu, Yunan Zhang, Shanshan Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High -Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9783030695378

It is an important yet challenging task to detect objects on hazy images in real-world applications. The major challenge comes from low visual quality and large haze density variations. In this work, we aim to jointly solve the image dehazing and the object detection tasks in real hazy scenarios by using haze density as prior knowledge. Our proposed Unified Dehazing and Detection (UDnD) framework consists of three parts: a residual-aware haze density classifier, a density-aware dehazing network, and a density-aware object detector. First, the classifier exploits the residuals of hazy images to accurately predict density levels, which provide rich domain knowledge for the subsequent two tasks. Then, we design respectively a High-Resolution Dehazing Network (HRDN) and a Faster R-CNN-based multi-domain object detector to leverage the extracted density information and tackle hazy object detection. Experiments demonstrate that UDnD performs favorably against other methods for object detection in real-world hazy scenes. Also, HRDN achieves better results than state-of-the-art dehazing methods in terms of PSNR and SSIM. Hence, HRDN can conduct haze removal effectively, based on which UDnD is able to provide high-quality detection results. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of an HPC-based Expert System to speed-up Retail Data Analysis using Residual Networks Combined with parallel Association Rule Mining and Scalable Recommenders 44

Design and Evaluation of an HPC-based Expert System to speed...

引用

44th International Convention on Information, Communication and Electronic Technology, MIPRO 2021

作者： Barakat, C. Riedel, M. Brynjolfsson, S. Cavallaro, G. Busch, J. Sedona, R. School of Engineering and Natural Sciences University of Iceland Iceland Jülich Supercomputing Centre Forschungszentrum Jülich Germany

ISBN: (纸本)9789532331011

Given the Covid-19 pandemic, the retail industry shifts many business models to enable more online purchases that produce large transaction data quantities (i.e., big data). Data science methods infer seasonal trends about products from this data and spikes in purchases, the effectiveness of advertising campaigns, or brand loyalty but require extensive processing power leveraging High-Performance Computing to deal with large transaction datasets. This paper proposes an High-Performance Computing-based expert system architectural design tailored for 'big data analysis' in the retail industry, providing data science methods and tools to speed up the data analysis with conceptual interoperability to commercial cloud-based services. Our expert system leverages an innovative Modular Supercomputer Architecture to enable the fast analysis by using parallel and distributed algorithms such as association rule mining (i.e., FP-Growth) and recommender methods (i.e., collaborative filtering). It enables the seamless use of accelerators of supercomputers or cloud-based systems to perform automated product tagging (i.e., residual deep learning networks for product image analysis) to obtain colour, shapes automatically, and other product features. We validate our expert system and its enhanced knowledge representation with commercial datasets obtained from our ON4OFF research project in a retail case study in the beauty sector. © 2021 Croatian Society MIPRO.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Code and Parameter Optimization for parallel and Scientific Computing

Code and Parameter Optimization for Parallel and Scientific ...

引用

作者： Nejahi, Younes Wayne State University

学位级别：Ph.D.

The increase in CPU cores and the growth of coprocessors and accelerators has given us a great performance advantage over the past few decades. However, to fully utilize these resources, developers face many challenges. In some cases, the problem is inherently serial in nature and dependencies prevent workload to be easily parallelizable. Memory bandwidth between host and accelerators can also become a bottleneck in data-intensive applications. There are methodologies developed by researchers to tackle each of these problems and in this work, we will study two optimization techniques at micro and macro levels. One class of problems is stencil operations which is a data-intensive algorithm. Stencil code is used in numerous areas such as computer simulations, partial differential equations, image processing, and cellular automata. To optimize this algorithm, micro-level optimization was performed to reduce the memory transaction required in the algorithm. NVIDIA warp shuffle technology allows developers to transfer data between threads without requiring to transfer to and from higher memory levels such as shared memory. Another class of problems is force field optimization of Monte Carlo simulation engines. Currently, experts spend months using heuristics and experience to find optimal values for force field parameters. This task can be done by computers using the brute-force method. However, it will require a significant amount of computational power to brute-force search space. To speed up the process simulations can be distributed between hundreds and thousands of nodes. To further optimize this problem we can use macro optimization methods such as Particle Swarm Optimization (PSO), and let the nodes communicate with each other like a swarm of birds. Using this methodology one can find an acceptable solution within a few days without any supervision. This work also proves that in some cases this approach could improve the best-known solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightweight HI source finding for next generation radio surveys

引用

ASTRONOMY AND COMPUTING 2022年 41卷

作者： Tolley, E. Korber, D. Galan, A. Peel, A. Sargent, M. T. Kneib, J. -P. Courbin, F. Starck, J. -L. Ecole Polytech Fed Lausanne EPFL Lab Astrophys Observ Sauverny CH-1290 Versoix Switzerland Ecole Polytech Fed Lausanne EPFL SCITAS CH-1015 Lausanne Switzerland Int Space Sci Inst Hallerstr 6 CH-3012 Bern Switzerland Univ Sussex Astron Ctr Dept Phys & Astron Brighton BN19QH E Sussex England CEA Saclay Dept Astrophys F-91191 Gif Sur Yvette France Ecole Polytech Fed Lausanne EPFL Lab Astrophys Observ Sauverny CH-1290 Versoix Switzerland

Future deep HI surveys will be essential for understanding the nature of galaxies and the content of the Universe. However, the large volume of these data will require distributed and automated processing techniques. We introduce LiSA, a set of python modules for the denoising, detection and characterization of HI sources in 3D spectral data. LiSA was developed and tested on the Square Kilometer Array Science Data Challenge 2 dataset, and contains modules and pipelines for easy domain decomposition and parallel execution. LiSA contains algorithms for 2D-1D wavelet denoising using the starlet transform and flexible source finding using null-hypothesis testing. These algorithms are lightweight and portable, needing only a few user-defined parameters reflecting the resolution of the data. LiSA also includes two convolutional neural networks developed to analyze data cubes which separate HI sources from artifacts and predict the HI source properties. All of these components are designed to be as modular as possible, allowing users to mix and match different components to create their ideal pipeline. We demonstrate the performance of the different components of LiSA on the SDC2 dataset, which is able to find 95% of HI sources with SNR > 3 and accurately predict their properties. (C) 2022 The Author(s). Published by Elsevier B.V.

关键词： methods Data analysis Techniques image processing

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：