检索结果-内蒙古大学图书馆

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenjie Wang Yehao Lu Guangcong Zheng Shuigen Zhan Xiaoqing Ye Zichang Tan Jingdong Wang Gaoang Wang Xi Li College of Computer Science and Technology Zhejiang University Polytechnic Institute Zhejiang University Baidu Zhejiang - Singapore Innovation and AI Joint Research Lab

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Vision-based roadside 3D object detection has attracted rising attention in autonomous driving domain, since it en-compasses inherent advantages in reducing blind spots and expanding perception range. While previous work mainly focuses on accurately estimating depth or height for 2D-to-3D mapping, ignoring the position approximation error in the voxel pooling process. Inspired by this insight, we propose a novel voxel pooling strategy to reduce such error, dubbed BEVSpread. Specifically, instead of bringing the image features contained in a frustum point to a single BEV grid, BEVSpread considers each frustum point as a source and spreads the image features to the surrounding BEV grids with adaptive weights. To achieve superior prop- agation performance, a specific weight function is designed to dynamically control the decay speed of the weights according to distance and depth. Aided by customized CUDA parallel acceleration, BEVSpread achieves comparable inference time as the original voxel pooling. Extensive experiments on two large-scale roadside benchmarks demonstrate that, as a plug-in, BEVSpread can significantly improve the performance of existing frustum-based BEV methods by a large margin of (1.12, 5.26, 3.01) AP in vehicle, pedestrian and cyclist. The source code will be made publicly available at BEVSpread.

关键词： Computer vision Three-dimensional displays Pedestrians Source coding Graphics processing units Object detection Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

8th International conference on Scale Space and Variational methods in Computer Vision, SSVM 2021

8th International Conference on Scale Space and Variational ...

引用

8th International conference on Scale Space and Variational methods in Computer Vision, SSVM 2021

ISBN: (纸本)9783030755485

The proceedings contain 45 papers. The special focus in this conference is on Scale Space and Variational methods in Computer Vision. The topics include: Multiscale Registration;challenges for Optical Flow Estimates in Elastography;an Anisotropic Selection Scheme for Variational Optical Flow methods with Order-Adaptive Regularisation;low-Rank Registration of images Captured Under Unknown, Varying Lighting;towards Efficient Time Stepping for Numerical Shape Correspondence;first Order Locally Orderless Registration;first-Order Geometric Multilevel Optimization for Discrete Tomography;bregman Proximal Gradient Algorithms for Deep Matrix Factorization;Hessian Initialization Strategies for -BFGS Solving Non-linear Inverse Problems;inverse Scale Space Iterations for Non-convex Variational Problems Using Functional Lifting;quantisation Scale-Spaces;A Scaled and Adaptive FISTA Algorithm for Signal-Dependent Sparse image Super-Resolution Problems;Convergence Properties of a Randomized Primal-Dual Algorithm with Applications to parallel MRI;wasserstein Generative Models for Patch-Based Texture Synthesis;sketched Learning for image Denoising;Translating Numerical Concepts for PDEs into Neural Architectures;CLIP: Cheap Lipschitz Training of Neural Networks;variational Models for Signal processing with Graph Neural Networks;synthetic images as a Regularity Prior for image Restoration Neural Networks;geometric Deformation on Objects: Unsupervised image Manipulation via Conjugation;learning Local Regularization for Variational image Restoration;Equivariant Deep Learning via Morphological and Linear Scale Space PDEs on the Space of Positions and Orientations;on the Correspondence Between Replicator Dynamics and Assignment Flows;learning Linear Assignment Flows for image Labeling via Exponential Integration;on the Geometric Mechanics of Assignment Flows for Metric Data Labeling;a Deep image Prior Learning Algorithm for Joint Selective Segmentation and Registration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OpenMedIA: Open-Source Medical image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms

arXiv

引用

arXiv 2022年

作者： Zhuang, Jia-Xin Huang, Xiansong Yang, Yang Chen, Jiancong Yu, Yue Gao, Wei Li, Ge Chen, Jie Zhang, Tong Peng Cheng Laboratory Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Electronic and Computer Engineering Peking University China National Laboratory for Parallel and Distributed Processing National University of Defense Technology China

In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms. Various medical image analysis methods, including 2D/3D medical image classification, segmentation, localisation, and detection, have been included in the toolbox with PyTorch and/or MindSpore implementations under heterogeneous NVIDIA and Huawei Ascend computing systems. To our best knowledge, OpenMedIA is the first open-source algorithm library providing compared PyTorch and MindSpore implementations and results on several benchmark datasets. The source codes and models are available at https://***/ OpenMedIA. © 2022, CC BY-NC-SA.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Federated Learning with Proximal Stochastic Variance Reduced Gradient Algorithms 20

Federated Learning with Proximal Stochastic Variance Reduced...

引用

49th International conference on parallel processing (ICPP)

作者： Dinh, Canh T. Tran, Nguyen H. Tuan Dung Nguyen Bao, Wei Zomaya, Albert Y. Zhou, Bing B. Univ Sydney Sydney NSW Australia Univ Melbourne Melbourne Vic Australia

ISBN: (纸本)9781450388160

Federated Learning (FL) is a fast-developing distributed machine learning technique involving the participation of a massive number of user devices. While FL has benefits of data privacy and the abundance of user-generated data, its challenges of heterogeneity across users' data and devices complicate algorithm design and convergence analysis. To tackle these challenges, we propose an algorithm that exploits proximal stochastic variance reduced gradient methods for non-convex FL. The proposed algorithm consists of two nested loops, which allow user devices to update their local models approximately up to an accuracy threshold (inner loop) before sending these local models to the server for global model update (outer loop). We characterize the convergence conditions for both local and global model updates and extract various insights from these conditions via the algorithm's parameter control. We also propose how to optimize these parameters such that the training time of FL is minimized. Experimental results not only validate the theoretical convergence but also show that the proposed algorithm outperforms existing Stochastic Gradient Descent-based methods in terms of convergence speed in FL setting.

关键词： distributed Machine Learning Federated Learning Stochastic Gradient Descent

来源：评论

学校读者我要写书评

暂无评论

Big data collaborative artificial intelligence and high-performance computing to drive physical design of fusion

Big data collaborative artificial intelligence and high-perf...

引用

2022 International conference on Cloud Computing, Big Data Applications and Software Engineering, CBASE 2022

作者： Liu, Pan Liu, Gongjie Liu, Jie Liu, Chencheng Xiong, Wenbin Tang, Zhangcun Zhou, Yinzhao Wang, Yonggang Yuan, Zhouming Beijng Paratera Technology Corp. Ltd Beijing100000 China National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory Changsha410073 China National University of Defense Technology Laboratory of Software Engineering for Complex Systems Changsha410073 China Central South University of Forestry and Technology Changsha410000 China Nuclear and Radiation Safety Center Mee Beijing100000 China University of Electronic Science and Technology of China Chengdu610000 China Tianfu Innovation Energy Establishment Chengdu610000 China

ISBN: (纸本)9798350396393

Controlled thermonuclear fusion has always been a dream pursued by mankind. However, the physical processes of controlled thermonuclear fusion are complex, requiring numerical simulations with high performance computing, and the amount of data generated by the physical processes on spatial, temporal and temperature scales is too large to be captured, managed, processed and collated in a reasonable time frame by mainstream software tools to achieve more aggressive fusion physical design. The data are too large to be captured, managed, processed, and collated into more aggressive targets for fusion physical design in a reasonable time by mainstream software tools. At the same time, the failure of fusion ignition can be caused by the distortion of various key physical quantities, and only by decomposing the process step by step and clarifying the changes of key physical quantities in the fusion physics process, can an effective mechanism be formed to prevent the distortion of key physical quantities from causing ignition failure in experimental physics. Big data in collaboration with artificial intelligence and high performance computing to drive the physical design of fusion is a novel avenue. By data acquisition with and pre-processing, this allows the creation of small sample libraries and deep learning. With supervised learning function convergence, incorporating solid/fluid computational methods, further network layering and cell expansion, the parameters of the physical model conforming to Lawson's criterion will become experimental physical parameters, and we find the new approach in Data capacity, Model combination approach, Type of material, Calculation speed, Optimisation of design iteration times, etc. are superior to the traditional approach. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

PPSS: A Privacy-Preserving Supervision Scheme Based on Blockchain

PPSS: A Privacy-Preserving Supervision Scheme Based on Block...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Ming Chen Peichang Shi Xiang Fu Feng Jiang Fei Gao Penghui Ma Jinzhu Kong National Key Laboratory of Parallel and Distributed Processing College of Computer Science National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems College of Computer Science National University of Defense Technology Changsha China Kylin Software Co.LTD Changsha China Zhejiang Lab Hangzhou China

In JointCloud Computing, multi-party participation introduces complexity and uncertainty. For all participants in JointCloud Computing, both continuous supervision and necessary privacy protection are required. Traditional supervision methods usually adopt the centralized information interaction mode, which has such defects as collusion of interests, single point of failure, privacy disclosure, etc. Building a decentralized supervision mechanism has become a new research direction. In this paper, we propose PPSS, a privacy-preserving supervision scheme based on blockchain, which decentralizes the supervision of the participants in JointCloud Computing, and combines the “double encryptions” and “threshold encryption” technologies to provide privacy protection. While making full use of the decentralization of the blockchain, a committee is established to carry out the analysis and decision-making tasks in terms of supervision and privacy protection. Experimental results indicate that PPSS can balance performance and security by reasonably configuring the committee.

关键词： Privacy Uncertainty Decision making Buildings Reliability engineering Blockchains Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Multi-operator feature enhancement methods for industrial defect detection 3

Multi-operator feature enhancement methods for industrial de...

引用

2021 3rd International conference on Artificial Intelligence Technologies and Applications, ICAITA 2021

作者： Zhou, Bo Fan, YiChao Liu, YuXin Yin, XuDong Department of Computer and Information Hefei University of Technology Anhui Xuancheng242000 China Department of Computer and Information Hefei University of Technology Anhui Hefei230000 China

Deep learning based object detection algorithms have been gradually applied to industrial defect detection, but the resulted accuracy does not fully meet the needs of industrial inspection. In order to enhance image features, this paper proposes a series of image preprocessing schemes based on edge detection operators, using a single-operator preprocessing scheme, a multi-operator serial preprocessing scheme and a multi-operator parallel preprocessing scheme for image preprocessing of data to enhance the edge features of images. The validation experiment of the SSD based object detection algorithm is performed on dataset used for industrial inspection, to verify the effectiveness of the processing schemes above. The result shows that the multi-operator based image preprocessing method is effective in improving the accuracy of surface defect detection in the field of industrial defect detection. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

TCN-Log2Vec: A Comprehensive Log Anomaly Detection Framework based on Optimized Log Parsing and Temporal Convolutional Network

TCN-Log2Vec: A Comprehensive Log Anomaly Detection Framework...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 IEEE International conference on

作者： Zhe Jiang Yali Gao Jie Yuan Kaiguo Yuan Xiaoyong Li Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education College of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

Logs that record execution information and system status, are useful for anomaly detection. Traditionally, developers manually checked logs through keyword search or rule matching. However, as the number of logs increases, this approach becomes unrealistic. More and more methods of log anomaly detection based on machine learning and deep learning have been proposed. In order to detect log anomalies accurately and effectively, this paper proposes a comprehensive framework, namely TCN-Log2Vec. Based on Drain, a prevalent and effective method to extract the log templates from the original logs, TCN-Log2Vec has done some optimization work in log parsing. It also captures sequence information, quantitative information, and semantic information from the original log. Meanwhile, it designs the anomaly detection module based on TCN (Temporal Convolutional Network) to achieve parallel processing. Our log parsing method achieves 99% accuracy on HDFS datasets and 94% accuracy on BGL datasets. We compare our anomaly detection framework with other advanced methods including DeepLog, LogAnomaly, and LogRobust, the experiment results show that our model has better performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single-scan Run Length Algorithm for Real-time Fiducial Marker Detection Based on FPGA Devices 22

Single-scan Run Length Algorithm for Real-time Fiducial Mark...

引用

Proceedings of the 2022 6th International conference on Video and image processing

作者： Farhana Binte Sufi Fernando Rincón Calle Jesús Barba Romero Juan Carlos López López Department of Electrical and Electronic Engineering University of Rajshahi Bangladesh Department of Technologies and Information Systems University of Castilla-La Mancha Spain

ISBN: (纸本)9781450397568

image processing pipelines involved in detecting markers from real-time video employ contour detection algorithms. Field Programmable Gate Arrays (FPGA) can provide greater computing power due to parallel processing and pipelining of the different stages in these algorithms. However, FPGA implementation of different contour detection methods remains challenging due to resource limitation and timing constraints. In this work a novel approach for a complete pipeline has been presented based on FPGA. The method used for the detection of fiducial markers from real-time video streams is based on a single-scan approach. Implementation of such pipeline into reconfigurable technology is specially challenging compared to software-oriented implementation as pointers, dynamic structures, efficient use of resources, etc. need to be considered. A driver is the need to fit the design into low-cost reconfigurable devices. To help face the related challenges of a hardware implementation High Level Synthesis (HLS) technology has been adopted, which implies reengineering of the reference algorithms. The results show a successful detection of markers over a dataset acquired in a controlled indoor environment with different resolutions at different distances. The proposal has been prototyped and tested on a Zedboard with Xilinx Zynq®-7000 SoC.

关键词： Single-scan run length algorithm Contour detection algorithm FPGA Stream processing Edge computer vision Fiducial markers HLS

来源：评论

学校读者我要写书评

暂无评论

Training Transformers Together 35

Training Transformers Together

引用

35th Annual conference on Neural Information processing Systems (NeurIPS)

作者： Borzunov, Alexander Ryabinin, Max Dettmers, Tim Lhoest, Quentin Saulnier, Lucile Diskin, Michael Jernite, Yacine Wolf, Thomas HSE Univ Yandex France Univ Washington Seattle WA USA Hugging Face New York NY USA

The infrastructure necessary for training state-of-the-art models is becoming overly expensive, which makes training such models affordable only to large corporations and institutions. Recent work proposes several methods for training such models collaboratively, i.e., by pooling together hardware from many independent parties and training a shared model over the Internet. In this demonstration, we collaboratively trained a text-to-image transformer similar to OpenAI DALL-E. We invited the viewers to join the ongoing training run, showing them instructions on how to contribute using the available hardware. We explained how to address the engineering challenges associated with such a training run (slow communication, limited memory, uneven performance between devices, and security concerns) and discussed how the viewers can set up collaborative training runs themselves. Finally, we show that the resulting model generates images of reasonable quality on a number of prompts.

关键词： distributed training volunteer computing transformers text-to-image memory efficiency communication efficiency heterogeneous hardware security

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：