检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Lawenda, Marcin Samborski, Krzesimir Khloponin, Kyrylo Szustak, Lukasz Poznan Supercomputing and Networking Center Jana Pawla II 10 Poznań61-139 Poland Czestochowa University of Technology Dąbrowskiego 69 Częstochowa42-201 Poland

This work is concerned with the evaluation of the performance of parallelization of learning and tuning processes for image classification and large language models. For machine learning model in image recognition, various parallelization methods are developed based on different hardware and software scenarios: simple data parallelism, distributed data parallelism, and distributed processing. A detailed description of presented strategies is given, highlighting the challenges and benefits of their application. Furthermore, the impact of different dataset types on the tuning process of large language models is investigated. Experiments show to what extent the task type affects the iteration time in a multi-GPU environment, offering valuable insights into the optimal data utilization strategies to improve model performance. Furthermore, this study leverages the built-in parallelization mechanisms of PyTorch that can facilitate these tasks. Furthermore, performance profiling is incorporated into the study to thoroughly evaluate the impact of memory and communication operations during the training/tuning procedure. Test scenarios are developed and tested with numerous benchmarks on the NVIDIA H100 architecture showing efficiency through selected metrics. © 2025, CC BY.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Multi-pass, Non-recursive Acoustic Echo Cancellation Sequential and parallel Algorithms 14th

Multi-pass, Non-recursive Acoustic Echo Cancellation Sequent...

引用

14th Asian Conference on Intelligent Information and Database Systems (ACiiDS)

作者： Walczynski, Maciej Wroclaw Univ Sci & Technol Wybrzeze Stanislawa Wyspianskiego 27 PL-50370 Wroclaw Poland

ISBN: (纸本)9783031219665;9783031219672

With few exceptions, the echo is a common phenomenon that occurs more or less during our talks. We then hear our own voice as a sound wave that bounced off the floor, walls, or other objects and returned to our ears. If the reflected sound comes back after a very short period of time, then it is perceived not as an echo, but as a kind of spectral distortion or reverberation, consisting of extending the sound. Depending on the situation, the occurrence of reverberation may or may not be desirable. When the time of arrival of reflections exceeds a certain value, it occurs as a separate sound that interferes with the reception of sound information. This paper will present methods of acoustic echo cancellation in telecommunication networks, in which parallel and distributed computing environments will be applied using multi-pass parallel algorithms based on non-recursive adaptive filtering.

关键词： Digital signal processing parallel computing Echo cancellation

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for image-text Matching

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

International Conference on parallel and distributed Systems (ICPADS)

作者： Yu Zhang Jianqiang Zhang Gongpeng Song Qin Lu Shuo Zhao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method.

关键词： Computer vision Fuses image matching Semantics Feature extraction Natural language processing

来源：评论

学校读者我要写书评

暂无评论

GPU-CUDA Implementation of the Third Order Gaussian Recursive Filter

引用

SN Computer Science 2022年第1期3卷 78页

作者： De Luca, Pasquale Galletti, Ardelio Marcellino, Livia Department of Computer Science University of Salerno via Giovanni Paolo II Fisciano Italy Department of Science and Technology University of Naples “Parthenope” Centro Direzionale C4 Naples Italy

Gaussian convolution operation is a fundamental procedure in several data analysis tasks and scientific fields. For example, Gaussian convolution is a central step in data assimilation and machine learning and it is also frequently used in image and signal processing. Gaussian recursive filters are a class of methods designed to approximate Gaussian convolutions in a fast way. In De Luca et al. (2019 15th international conference on signal-image technology and internet-based systems (SITIS), pp 941–648, 2019), we presented a parallel implementation of the K-iterated first-order Gaussian recursive filter. This algorithm has been proved to be very efficient and accurate. Here, we provide a new GPU-parallel implementation which is based on the third order recursive filter. This filter guarantees larger accuracy and a lower computational cost with respect to the first-order one. To manage an efficient memory strategy access, and to achieve better performance results, our algorithm exploits the CUDA capabilities available on the GPU environment. Results in terms of performance and accuracy are provided in tests and experiments. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2021.

关键词： CUDA Gaussian convolution GPU Recursive filter

来源：评论

学校读者我要写书评

暂无评论

A Multi-staining Digital Pathology image Registration Method Based on Global and Local Computing

A Multi-staining Digital Pathology Image Registration Method...

引用

ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and parallel/distributed Computing (SNPD)

作者： Yi Ding Xin Zhang Cheng Lu School of Computer and Cyber Sciences Communication University of China Beijing China Department of Radiology Guangdong Provincial People’s Hospital Guangzhou China

ISBN: (数字)9798350391954

ISBN: (纸本)9798350391961

To accurately evaluate the patient’s condition, medical workers usually need to register multiple pathological images of the lesion site samples. Using computer technology to assist in registration work can effectively improve the efficiency of doctors analyzing pathological images. One of the most advanced methods currently is the Virtual Alignment of Pathology image Series method, which is a multi-staining digital pathology image registration method that combines global and local calculations. However, this method may encounter certain biases when processing images with significant angle differences. Through a detailed analysis of this method, this article proposes an improvement plan which optimizes the acquisition of non-rigid registration mask images, enabling the method to obtain mask images more reasonably and achieve better registration results for images with significant angle differences. This provides more accurate judgment basis and helps doctors diagnose and develop treatment plans more accurately.

关键词： Pathology Solid modeling image registration Accuracy Medical services Software Registers

来源：评论

学校读者我要写书评

暂无评论

CDCP: A Framework for Accelerating Dynamic Channel Pruning methods

CDCP: A Framework for Accelerating Dynamic Channel Pruning M...

引用

International Conference on parallel and distributed Systems (ICPADS)

作者： Zhaohong Xiang Yigui Luo Yin Xie Haihong She Weiming Liang Laigang Zhao School of Software Engineering Tongji University Shanghai China Aichi Automobile (Shanghai) Company Limited

Dynamic channel pruning is a technique aimed at reducing the theoretical computational complexity and inference latency of convolutional neural networks. Dynamic channel pruning methods introduce complex additional modules for dynamically selecting channels for images. Due to the additional modules, dynamic channel pruning methods never achieve optimal acceleration effect in real world. To address this problem, we propose Consecutive Dynamic Channel Pruning (CDCP), a novel dynamic channel pruning framework unified for almost all dynamic pruning methods designed for continuous image processing. The core idea of CDCP stems from our observation that adjusting the network for all frames in semantically continuous scenes is unnecessary since adjacent frames often share similar network structures in dynamic channel pruning. CDCP introduces a simple binary classifier to determine whether the network structure needs to be adjusted for a new frame. Our method can also be used for semantically non-continuous image processing tasks with a slightly lower probability of model reuse. We validate the effectiveness of CDCP on three dynamic channel pruning methods and better acceleration effects are achieved when applied them with CDCP to the semantically continuous Waymo dataset, the nuScenes dataset, and the semantically discontinuous COCO dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

image Distillation Based Screening for X-ray Crystallography Diffraction images 19

Image Distillation Based Screening for X-ray Crystallography...

引用

19th IEEE International Symposium on parallel and distributed processing with Applications (IEEE ISPA)

作者： Chen, Lingyao Xu, Kang Zheng, Xiaoying Zhu, Yongxin Jing, Yi Shanghai Informat Technol Res Ctr Shanghai 201210 Peoples R China Chinese Acad Sci Shanghai Adv Res Inst Shanghai 201210 Peoples R China

ISBN: (纸本)9781665435741

The modern synchrotron radiation facilities are producing massive diffraction images, which present a severe problem for data processing due to the high dimensionality of imaging data. Feature recognition and selection based deep learning methods have been developed to analyze data automatically. One crucial step is to use AI to screen out the diffraction images without Bragg spots. This paper proposes a feature distillation based approach for screening. It helps to reduce over 40% raw data volume and greatly alleviates the post processing workload faced by scientists.

关键词： Deep Learning Neural Networks Bragg Spot serial crystallography

来源：评论

学校读者我要写书评

暂无评论

Ancient Chinese Character image Retrieval Based on Fusing Deep Features and Skeleton Features

Ancient Chinese Character Image Retrieval Based on Fusing De...

引用

International Conference on parallel and distributed Systems (ICPADS)

作者： Xinhui Wang Xuedong Tian School of Cyber Security and Computer Hebei University Baoding China Institute of Intelligent Image and Document Information Processing Hebei University Baoding China

The complex glyph structures and diverse writing styles of ancient Chinese character images lead to suboptimal performance when existing image retrieval methods are directly applied to datasets of these images. Addressing the impact on retrieval caused by the complex glyph structure and rich detail information characteristic of ancient Chinese character images, a multi-layer feature adaptive fusion model for ancient Chinese character image retrieval is designed. Firstly, a local feature extraction module is constructed to obtain low-level feature maps with different spatial receptive fields. Secondly, to better fuse features of varying scales, an improved ASFF(Adaptively Spatial Feature Fusion) method is employed to build the PSASFF(Pixel Shuffle Adaptively Spatial Feature Fusion) module for adaptive fusion of multi-layer features extracted by the designed network. Finally, in order to reduce the influence of the writing style of ancient Chinese characters on retrieval, the cosine similarity scores of image retrieval before and after fine processing are weighted and used as the ultimate similarity scores. The retrieval method proposed achieves an average retrieval accuracy of mAP@50 and mAP@30 of 0.8537 and 0.9576 respectively on the ancient Chinese character image dataset. Experimental results demonstrate the effectiveness of this method for ancient Chinese character image retrieval.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Counting people in the crowd using social media images for crowd management in city events

引用

TRANSPORTATION 2021年第6期48卷 3085-3119页

作者： Gong, V. X. Daamen, W. Bozzon, A. Hoogendoorn, S. P. Delft Univ Technol Fac Civil Engn & Geosci Stevinweg 1 NL-2628 CN Delft Netherlands Delft Univ Technol Fac Elect Engn Math & Comp Sci Mekelweg 4 NL-2628 CD Delft Netherlands

City events are getting popular and are attracting a large number of people. This increase needs for methods and tools to provide stakeholders with crowd size information for crowd management purposes. Previous works proposed a large number of methods to count the crowd using different data in various contexts, but no methods proposed using social media images in city events and no datasets exist to evaluate the effectiveness of these methods. In this study we investigate how social media images can be used to estimate the crowd size in city events. We construct a social media dataset, compare the effectiveness of face recognition, object recognition, and cascaded methods for crowd size estimation, and investigate the impact of image characteristics on the performance of selected methods. Results show that object recognition based methods, reach the highest accuracy in estimating the crowd size using social media images in city events. We also found that face recognition and object recognition methods are more suitable to estimate the crowd size for social media images which are taken in parallel view, with selfies covering people in full face and in which the persons in the background have the same distance to the camera. However, cascaded methods are more suitable for images taken from top view with gatherings distributed in gradient. The created social media dataset is essential for selecting image characteristics and evaluating the accuracy of people counting methods in an urban event context.

关键词： Crowd size estimation Social media analysis image processing Face recognition Input for crowd management

来源：评论

学校读者我要写书评

暂无评论

Research and Suggestions for Evaluation Metrics of On-board Video Desensitization

Research and Suggestions for Evaluation Metrics of On-board ...

引用

Information Science, parallel and distributed Systems (ISPDS), International Conference on

作者： Xiaolong Huang Te Hu Haojie Ji Yupeng Chen Wangdong Lu Peng He Guowei Sun Jingyan Wang State Key Laboratory of Intelligent Vehicle Safety Technology Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China China Automotive Engineering Research Institute Co. Ltd Chongqing China Zhongtong Bus Holding Co. Ltd Liaocheng China

ISBN: (数字)9798350352719

ISBN: (纸本)9798350352726

Sensitive data leakage has become an urgent problem to be solved as more images based functionalities are being developed in vehicles. However, there is a scarcity of evaluation for on-board videos data desensitization. This research analyzes on-board video desensitization process including the image pre-processing stage, sensitive area localization stage and sensitive area desensitization stage. Considering that, this paper presents several evaluation methods and metrics of sensitive target detection performance, privacy-utility evaluation of video file metadata and image, so as to provide reference for the related research on the desensitization evaluation of on-board video.

关键词： Measurement Location awareness Information science Target recognition Current measurement distributed databases Object detection

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：