检索结果-内蒙古大学图书馆

3rd Asia-Pacific conference on image processing, Electronics and Computers, IPEC 2022

作者： Yuan, Min College of Asian-European Languages Xi'an Fanyi University Xi'an710128 China

ISBN: (纸本)9781450395786

Tourism is closely related to people's lives today, and the development level of tourism informatization is an important indicator to measure the modern tourism industry. At present, more and more data on the Internet is released in the form of linked data, which reduces the complexity of the integration of distributed, heterogeneous or autonomous data, and at the same time promotes the application of linked data. The purpose of this article is to model the influence of Seoul's city image on tourists' willingness to revisit based on parallel computing. This paper studies the similarity calculation efficiency in the data set of passenger-related passenger revisiting intention resources. According to the established tourist tourism ontology, this paper adopts the MapReduce parallel computing framework to design a parallel computing method of related data similarity to improve the discovery efficiency of the related data model of the willingness of large-scale tourists to revisit. Experimental research shows that this article analyzes the difference in perceptions of various image factors by tourists of different ages, and finds that the value in the single-factor analysis of variance table is greater than 0.05, indicating that tourists of different ages do not have significant perceptions of each image factor. © 2022 ACM.

关键词： Linked data

来源：评论

学校读者我要写书评

暂无评论

DEF-Net: A Face Aging Model by Using Different Emotional Learnings

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第5期32卷 3012-3022页

作者： Duan, Mingxing Li, Kenli Liao, Qing Tian, Qi Hunan Univ Sch Informat Sci & Engn Changsha 410082 Peoples R China Natl Univ Def Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Hunan Univ Coll Informat Sci & Engn Changsha 410082 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Guangdong Peoples R China Huawei Technol Cloud BU Shenzhen 518000 Guangdong Peoples R China

Face aging has attracted widespread attention in recent years, but most studies are based on the same emotional situation. Is the same person's aging in different emotional situations the same? To solve the above confusion, this paper proposes a novel face aging model DEF-Net, which consists of two parts: different emotional learnings (Emotion-Net) and face aging (Age-Net). Given a target emotion category, DEF-Net first assists the image from the original dataset to learn the emotion features through Emotion-Net and the generated dataset is used as the inputs of Age-Net. At the same time, multiple loss functions are used to ensure that the crucial information of the original image is not lost. Secondly, Age-Net, which has been pre-trained on the original dataset, began to adopt the generated dataset to learn the aging distribution under different emotions. Designed loss functions are utilized to ensure that the realistic target images generated by Age-Net do not lose the learned emotional characteristics. Finally, extensive experiments are used to verify the performance of DEF-Net. Compared with other state-of-the-art methods: (1) DEF-Net can learn different facial emotions across different datasets and generate corresponding realistic aging images;(2) the results achieved by our DEF-Net are demonstrated to be better than those by the model that performs face aging first and then learns different emotional characteristics.

关键词： Faces Aging Generative adversarial networks Training image reconstruction Task analysis Shape Age-net emotion-net face aging loss functions

来源：评论

学校读者我要写书评

暂无评论

Fast iterative method empowered by GPU acceleration for Fourier-domain optical coherence tomography image reconstruction 27

Fast iterative method empowered by GPU acceleration for Four...

引用

conference on Optical Coherence Tomography and Coherence Domain Optical methods in Biomedicine XXVII

作者： Wang, Mengyuan Dong, Zhenxing Ling, Yuye Su, Yikai Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Elect Engn State Key Lab Adv Opt Commun Syst & Networks Shanghai Peoples R China

ISBN: (纸本)9781510658394;9781510658400

Iterative methods could provide high-quality image reconstruction for Fourier-domain optical coherence tomography (FD-OCT) by solving an inverse problem. Compared with the regular IFFT-based reconstruction, a more accurate estimation could be iteratively solved by integrating prior knowledge, however, it is often more time-consuming. To deal with the time problem, we proposed a fast iterative method for FD-OCT image reconstruction empowered by GPU acceleration. An iterative scheme is adopted, including a forward model and an inverse solver. Large-scale parallelism of OCT image reconstruction is performed on B-scans. We deployed the framework on Nvidia GeForce RTX 3090 graphic card that enables parallel processing. With the widely used toolkit Pytorch, the inverse problem of OCT image reconstruction is solved by the stochastic gradient descent (SGD) algorithm. To validate the effectiveness of the proposed method, we compare the computational time and image quality with other iterative approaches including ADMM, AR, and RFIAA method. The proposed method could provide a significant speed enhancement of 1,500 times with comparable image quality to that of ADMM reconstruction. The result indicates a potential for high-quality real-time volumetric OCT image reconstruction via iterative algorithms.

关键词： OCT image reconstruction GPU acceleration iterative method B-scan-based

来源：评论

学校读者我要写书评

暂无评论

Frequency-Domain Guided Multiple parallel Kernels Network for Low-Light Remote Sensing image Enhancement

Frequency-Domain Guided Multiple Parallel Kernels Network fo...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jingxuan Zhou Hao Li Jinlong Wang Xiongxin Tang Fanjiang Xu Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Due to dark environments, optical aberrations, etc, the remote sensing images are often submerged under low contrast degradation, which greatly hinders their practical applications for agricultural management and other related tasks. The surface features of remote sensing images are often continuously distributed in space, thus, the sizes of the network’s receptive fields and its ability to learn long-range dependencies are crucial for restoring low-light remote sensing images. Existing methods based on CNN provide limited receptive fields, while Transformer-based methods are constrained by their quadratic computational complexity. To cope with these issues, we propose a novel low-light remote sensing image enhancement network that combines multi-scale receptive fields with frequency-domain attention. Specifically, this network employs multiple parallel kernels of varying sizes to learn multi-scale local features in the spatial domain and complements frequency-domain information to learn global long-range correlations, which achieves local-global feature extraction and further facilitates subsequent degraded images enhancement. We have conducted extensive experiments to demonstrate that our network outperforms existing methods quantitatively and achieves exceptional visual performance, which fully highlights the effectiveness and superiority of our method in enhancing low-light remote sensing images.

关键词： Visualization Frequency-domain analysis Transforms Speech enhancement Feature extraction Transformers image restoration Kernel Remote sensing image enhancement

来源：评论

学校读者我要写书评

暂无评论

Configurable synthetic application for studying malleability in HPC 31

Configurable synthetic application for studying malleability...

引用

31st Euromicro International conference on parallel, distributed and Network-Based processing, PDP 2023

作者： Martin-Alvarez, Iker Aliaga, Jose I. Castillo, Maribel Iserte, Sergio Universitat Jaume I Dept. Ing. y Ciencia de Computadores Castellón Spain Spain

ISBN: (纸本)9798350337631

Nowadays, the throughput improvement in large clusters of computers recommends the development of malleable applications. Thus, during the execution of these applications in a job, the resource management system (RMS) can modify its resource allocation, in order to increase the global throughput. There are different alternatives to complete the different steps in which the reallocation of resources is decomposed. To find the best alternatives, this paper introduces a configurable synthetic iterative MPI malleable application capable of modifying, in execution time, the number of MPI processes according to several parameters. The application includes a performance module to measure stages time within steps, from processes management to data redistribution. In this way, the analysis of different scenarios will allow to conclude how the reconfiguration of application has to be made in different circumstances. At the same time, this tool can be used to create workloads that will allow to analyse the impact of malleability on a system and the work in progress. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

U-shaped Dual Attention Transformer: An Efficient Transformer Based on Channel and Spatial Attention 4

U-shaped Dual Attention Transformer: An Efficient Transforme...

引用

4th International conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2024

作者： Zhai, Zhaoyuan Qiao, Peng Li, Rongchun Zhou, Zhen National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing Changsha China

ISBN: (纸本)9798331531225

Transformer-based methods have demonstrated remarkable performance on image super-resolution tasks. Due to high computational complexity, researchers have been working to achieve a balance between computation costs and performance. Restormer has achieved commendable balance by utilizing global channel attention. However, the performance is limited by insufficient local pixel reconstruction. In this paper, we propose a U-shaped Dual Attention Transformer (UDAT) with local-global receptive field, addressing the limitation of Restormer in local pixel reconstruction. We propose a dense window channel attention to enhance the local feature representation, more efficient in computational complexity. Experiments demonstrate that our UDAT achieve superior performance compared with Restormer on benchmark datasets, surpassing Restormer by 0.57 dB on the Urban100 dataset. On-par with SwinIR, our method reduces computational complexity by 3.2 times and improves inference speed by 2 times, achieving a better balance between computational costs and performance. © 2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Communication Overlapping Pipelined Conjugate Gradients for distributed Memory Systems and Heterogeneous Architectures 27th

Communication Overlapping Pipelined Conjugate Gradients for ...

引用

27th International European conference on parallel and distributed Computing (Euro-Par)

作者： Tiwari, Manasi Vadhiyar, Sathish Indian Inst Sci Dept Computat & Data Sci Bangalore Karnataka India

ISBN: (纸本)9783031061561;9783031061554

Preconditioned Conjugate Gradient (PCG) method has been one of the widely used methods for solving linear systems of equations for sparse problems. Pipelined PCG (PIPECG) attempts to eliminate the dependencies in the computations in the PCG algorithm and overlap non-dependent computations by reorganizing the traditional PCG code and using non-blocking allreduces . We have developed a novel pipelined PCG algorithm called PIPECG-OATI (One Allreduce per Two Iterations) which reduces the number of non-blocking allreduces to one per two iterations and provides large overlap of global communication and computations at higher number of cores in distributed memory CPU systems. PIPECG-OATI gives up to 3x speedup over PCG and 1.73x speedup over PIPECG at large number of cores. For GPU accelerated heterogeneous architectures, we have developed three methods for efficient execution of the PIPECG algorithm. These methods achieve task and data parallelism. Our methods give considerable performance improvements over PCG CPU and GPU implementations of Paralution and PETSc libraries.

关键词： Preconditioned Conjugate Gradient Overlapping communication and computations distributed memory systems Heterogeneous architectures

来源：评论

学校读者我要写书评

暂无评论

51st International conference on parallel processing, ICPP 2022 - Main conference Proceedings

51st International Conference on Parallel Processing, ICPP 2...

引用

51st International conference on parallel processing, ICPP 2022

ISBN: (纸本)9781450397339

The proceedings contain 88 papers. The topics discussed include: HSP: hybrid synchronous parallelism for fast distributed deep learning;adaptive and efficient GPU time sharing for hyperparameter tuning in cloud;TCB: accelerating transformer inference services with request concatenation;EmbRace: accelerating sparse communication for distributed training of deep neural networks;FedHiSyn: a hierarchical synchronous federated learning framework for resource and data heterogeneity;parallel algorithms for masked sparse matrix-matrix products;tesseract: parallelize the tensor parallelism efficiently;automatic differentiation of parallel loops with formal methods;a single-tree algorithm to compute Euclidean minimum spanning tree on GPUs;efficient phase-functioned real-time character control in mobile games: a TVM enabled approach;and SHE: a generic framework for data stream mining over sliding windows.

关键词：

来源：评论

学校读者我要写书评

暂无评论

distributed methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees 36

Distributed Methods with Compressed Communication for Solvin...

引用

36th conference on Neural Information processing Systems (NeurIPS)

作者： Beznosikov, Aleksandr Richtarik, Peter Diskin, Michael Ryabinin, Max Gasnikov, Alexander Innopolis Univ Innopolis Russia MIPT Dolgoprudnyi Russia HSE Univ Moscow Russia Yandex Moscow Russia KAUSTI Riyadh Saudi Arabia RAS IITP Moscow Russia Innopolis Univ Res Ctr Artificial Intelligence Innopolis Russia

ISBN: (纸本)9781713871088

Variational inequalities in general and saddle point problems in particular are increasingly relevant in machine learning applications, including adversarial learning, GANs, transport and robust optimization. With increasing data and problem sizes necessary to train high performing models across various applications, we need to rely on parallel and distributed computing. However, in distributed training, communication among the compute nodes is a key bottleneck during training, and this problem is exacerbated for high dimensional and over-parameterized models. Due to these considerations, it is important to equip existing methods with strategies that would allow to reduce the volume of transmitted information during training while obtaining a model of comparable quality. In this paper, we present the first theoretically grounded distributed methods for solving variational inequalities and saddle point problems using compressed communication: MASHA1 and MASHA2. Our theory and methods allow for the use of both unbiased (such as Randk;MASHA1) and contractive (such as Topk;MASHA2) compressors. New algorithms support bidirectional compressions, and also can be modified for stochastic setting with batches and for federated learning with partial participation of clients. We empirically validated our conclusions using two experimental setups: a standard bilinear min-max problem, and large-scale distributed adversarial training of transformers.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Single image Defocus Deblurring with Progressive Feature Attention Network 14

Single Image Defocus Deblurring with Progressive Feature Att...

引用

14th International conference on Electronics, Communications and Networks, CECNet 2024

作者： Zhan, Hongmin Ling, Shenggui Shi, Rui School of Computer Science and Engineering Sichuan University of Science & Engineering China Key Lab. of Higher Educ. of Sichuan Prov. for Enterprise Informationalization and Internet of Things Sichuan University of Science and Engineering China

ISBN: (纸本)9781643685632

The goal of single-image defocus deblurring is to reconstruct a clear image from a defocused one. Although existing methods perform well in common blurry scenes, they still face the challenge of feature extraction when meeting severely defocused areas. Therefore, the innovative progressive multi-scale feature extraction module (PMFEM) and the feature attention module (FAM) are proposed. The PMFEM gradually extracts and fuses multi-scale features through convolution kernels of different sizes. Three parallel paths process the input respectively, simplifying and optimizing the feature extraction process layer by layer to achieve progressive processing. The FAM dynamically enhances or suppresses features of specific scales by fusing multi-path feature information, thereby improving the model's feature expression ability. Experimental results show that our method achieves state-of-the-art performance on the Dual-Pixel Defocus Deblurring (DPDD) and Regression Tree Fields (RTF) datasets. Our code can be obtained at https://***/HMin-Z/PFANet. © 2024 The Authors.

关键词： image reconstruction

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：