检索结果-内蒙古大学图书馆

2021 2nd International Workshop on Electronic communication and Artificial Intelligence, IWECAI 2021

作者： Yang, Jie Xie, Zhihong Li, Ping School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Changsha Hunan410114 China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha Changsha Hunan410114 China

Deep convolutional neural networks have been widely used in various AI applications. The most advanced neural networks are becoming deeper and wider, which has caused some large convolutional neural networks to exceed the size limit of the server or application. The pruning algorithm provides a way to reduce the size of the neural network while keeping the accuracy as high as possible. The automatic progressive pruning algorithm is one of the widely used pruning algorithms. The progressive pruning algorithm prunes a certain layer of the network in each iteration to reduce the sparsity while preserving the accuracy as much as possible. In this article, we design a new automatic progressive pruning algorithm named MultiAdapt. MultiAdapt combines the combination method and the greedy algorithm. This multi-layers progressive pruning method greatly increases the search space of the greedy algorithm, making it possible to obtain a better pruning network. We use MultiAdapt to prune large neural networks VGG-16 and ResNet. The experimental results show that the MultiAdapt algorithm is better than other mainstream methods in the balance of neural network model size and accuracy. For image classification tasks on the ImageNet dataset, our method achieved 88.72% and 90.55% TOP-5 accuracy on the 50% sparsity VGG-16 and ResNet, while obtaining nearly 2 reduction in parameters and floating point numbers. The operation is reduced, and the reduction is higher than the recent popular method. © Published under licence by IOP Publishing Ltd.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Image Matching Algorithm Under Adverse Conditions Based on SIFT 14

Image Matching Algorithm Under Adverse Conditions Based on S...

引用

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Chen, Hao Cao, Xinrong Li, Zuoyong Lin, Lihui Fuzhou University College of Computer and Big Data Fuzhou350108 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Fuzhou350121 China Wuyi University Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry School of Mathematics and Computer Science Fujian354300 China

ISBN: (纸本)9798350356670

Image matching technology is crucial in computer vision applications. However, the traditional SIFT (Scale-Invariant Feature Transform) algorithm often faces challenges under adverse conditions, such as a high number of mismatched points and few accurately matched points. Additionally, in practical scenarios, environmental factors like lighting changes and image blurring further reduce image similarity. Therefore, this paper proposes an improved SIFT-based image matching algorithm to address these challenges. First, SIFT is used to extract image features, and a bidirectional FLANN (Fast Library for Approximate Nearest Neighbors) matching strategy is employed to initially filter out incorrect features. Then, the RANSAC (Random Sample Consensus) algorithm is used to screen out unreliable matching point pairs. Finally, the matching accuracy is evaluated based on the remaining pure matching point pairs. Experimental results demonstrate that, compared to the traditional SIFT algorithm, this improved algorithm achieves higher matching accuracy and robustness under adverse conditions, exhibiting superior performance. © 2024 IEEE.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

An Asynchronous Clustering and Mobile data Gathering Schema Based on Timer Mechanism in Wireless Sensor Networks

引用

Computers, Materials & Continua 2019年第3期58卷 711-725页

作者： Jin Wang Yu Gao Wei Liu Wenbing Wu Se-Jung Lim Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer&Communication EngineeringChangsha University of Science&TechnologyChangsha410114China School of Information Science and Engineering Fujian University of TechnologyFuzhou350000China College of Information Engineering Yangzhou UniversityYangzhou225000China Department of Computer Engineering Chonnam National UniversityYeosu596597Korea.

Recently,Wireless sensor networks(WSNs)have become very popular research topics which are applied to many *** provide pervasive computing services and techniques in various potential applications for the Internet of Things(IoT).An Asynchronous Clustering and Mobile data Gathering based on Timer Mechanism(ACMDGTM)algorithm is proposed which would mitigate the problem of“hot spots”among sensors to enhance the lifetime of *** clustering process takes sensors’location and residual energy into consideration to elect suitable cluster ***,one mobile sink node is employed to access cluster heads in accordance with the data overflow time and moving time from cluster heads to *** experimental results display that the presented method can avoid long distance communicate between sensor ***,this algorithm reduces energy consumption effectively and improves package delivery rate.

关键词： Internet of things wireless sensor networks clustering mobile data collection timer.

来源：评论

学校读者我要写书评

暂无评论

RSSD: Object Detection via Attention Regions in SSD Detector

RSSD: Object Detection via Attention Regions in SSD Detector

引用

IEEE International Conference of Safety Produce Informatization (IICSPI)

作者： Shuren Zhou Jia Qiu Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha China

ISBN: (数字)9781728145662

ISBN: (纸本)9781728145679

This paper designs a module of attention regions in SSD detector for accurate and efficient object detection (RSSD). Different from previous one-stage detection method like SSD which just simply applied the multi-scale head-features and directly extracted from backbone network, for classification and regression, our method aims to strengthen the characterization of head-features further. The parallel encode-to-decode structure is constructed and a computation method of regional distribution on features (R-Softmax) is proposed. What's more, in order to reduce time-costs, the down-sampling layers are shared with the multi-scale layers from backbone network. Our detector performs better on PASCAL VOC datasets (e.g., 78.4% mAP V.S. SSD 76.4% on VOC 07test) and costs 0.001s per image more than SSD.

关键词： Object detection Training Convolution Feature extraction Detectors Proposals Mathematical model

来源：评论

学校读者我要写书评

暂无评论

IF-Font: Ideographic Description Sequence-Following Font Generation 38

IF-Font: Ideographic Description Sequence-Following Font Gen...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Chen, Xinping Ke, Xiao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-view Label and Feature Supervision Network for Semi-supervised Medical Image Segmentation 24

Dual-view Label and Feature Supervision Network for Semi-sup...

引用

7th International Conference on Signal processing and Machine Learning, SPML 2024

作者： Zhou, Zhen Li, Zuoyong Wang, Zhengyuan Teng, Shenghua Wang, Tao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (纸本)9798400717192

Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to improve performance. However, most existing semi-supervised segmentation methods exhibit shortcomings in supervising unlabeled data, both in the label space due to potential noise in pseudo-labels, and the feature space due to indistinct class boundaries. To address the issues above, we propose Dual-view Label and Feature Supervision Network, termed DLFS-Net, to enhance label and feature supervision for unlabeled data. Our approach is based on a dual-view learning strategy that incorporates two modules: the Confidence Fusion Supervision Module (CFS) and the Dual-view Prototype Learning Module (DPL). Specifically, the CFS module generates weight matrices to integrate complementary information from two model outputs, producing more accurate pseudo-labels in the label space. The DPL module reduces intra-class variations in the feature space from two different views through prototype learning to generate clear class boundaries. Experiments on the LA and Pancreas-CT datasets demonstrate that our framework show solid gains (e.g.,1.76% Dice and 2.37% Jaccard improvement on Pancreas-CT dataset with 20% labeled data) compared with the state-of-the-art methods. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Unsigned Road Incidents Detection Using Improved RESNET from Driver-view Images

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期6卷 1203-1216页

作者： Li, Changping Wang, Bingshu Zheng, Jiangbin Zhang, Yongjun Chen, C.L. Philip Northwestern Polytechnical University School of Software Xi'an710129 China Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Frequent road incidents cause significant physical harm and economic losses globally. The key to ensuring road safety lies in accurately perceiving surrounding road incidents. However, the highly dynamic nature of traffic introduces significant challenges, particularly in detecting sudden and temporary incidents. In this paper, we propose a novel detection framework, Multi-head Attention ResNet with Dynamic Bottleneck (DB_RESNET_MHA), to identify physical unsigned road incidents. Our approach introduces three key innovations. First, we develop a tailored data augmentation strategy to create images that closely mimic the complex variations found in real-world road environments. Second, we enhance model expressiveness by employing attention mechanisms to nonlinearly integrate convolutional kernels within the residual network. Furthermore, we refine the prediction head by applying spatially distinct attention weights, enabling the model to capture intricate correlations between different features more effectively. To demonstrate the effectiveness of our method, we create a dataset for unsigned road incidents (UnsignRI), comprising a total of 16,323 images that capture 12 distinct types of incidents. It stands out as the most comprehensive dataset in the field, encompassing a wide range of geographical features and incident categories. Experimental results show that DB_RESNET_MHA achieves an average accuracy of 96.2% and a f1-score of 0.955 across various categories of unsigned incidents, surpassing other models. © 2020 IEEE.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Reversible Natural Language Watermarking Using Synonym Substitution and Arithmetic Coding

引用

Computers, Materials & Continua 2018年第6期55卷 541-559页

作者： Lingyun Xiang Yan Li Wei Hao Peng Yang Xiaobo Shen Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha 410114HunanChina School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha 410114HunanChina School of Traffic&Transportation Engineering Changsha University of Science&TechnologyChangsha 410114HunanChina Hunan Branch of CNCERT/CC Changsha 410004HunanChina School of Computer Science and Engineering Nanyang Technological University639798Singapore

For protecting the copyright of a text and recovering its original content harmlessly,this paper proposes a novel reversible natural language watermarking method that combines arithmetic coding and synonym substitution *** analyzing relative frequencies of synonymous words,synonyms employed for carrying payload are quantized into an unbalanced and redundant binary *** quantized binary sequence is compressed by adaptive binary arithmetic coding losslessly to provide a spare for accommodating additional ***,the compressed data appended with the watermark are embedded into the cover text via synonym substitutions in an invertible *** the receiver side,the watermark and compressed data can be extracted by decoding the values of synonyms in the watermarked text,as a result of which the original context can be perfectly recovered by decompressing the extracted compressed data and substituting the replaced synonyms with their original *** results demonstrate that the proposed method can extract the watermark successfully and achieve a lossless recovery of the original ***,it achieves a high embedding capacity.

关键词： Arithmetic coding synonym substitution lossless compression reversible watermarking.

来源：评论

学校读者我要写书评

暂无评论

How to fast verify collatz conjecture by automata 21

How to fast verify collatz conjecture by automata

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Ren, Wei Xiao, Ruiyang School of Computer Science China University of Geoseciences Wuhan430074 China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guizhou China

ISBN: (纸本)9781728120584

To verify Collatz conjecture for a given integer, we need to justify whether or not the given starting number goes to 1 finally. Current method computes 3∗x+1 and x/2 one by one. In this paper, we propose an automata-based algorithm to compute the process in a batch with m steps - (3∗x+1)2 or x/2. We also propose reduced Collatz conjecture and we prove it is equivalent to Collazt conjecture. We also point out that original dynamics is the combination of reduced dynamics. (Original dynamics is a serial of occurred 3∗x+1 and x/2 computation in the process from a starting number to 1;Reduced dynamics is a serial of occurred 3∗x+1 and x/2 computation in the process from a starting number to the first transformed number that is less than the starting number.) We study the properties of reduced dynamics and discover that reduced dynamics for some starting numbers can be determined directly without conducting concrete 3∗x+1 or x/2 computations. We build a binary tree called Collatz tree and use it as a visual tool for automata design. We find that each partition of starting number residue class decides the further computation is whether 3∗x+1 or x/2. The proposed automata can output code segment with m+2 computations in terms of (3∗x+1)/2 or x/2 by taking as input x=4t+3, where t is in residue class i module 2m and m is a natural number. We finally propose a conjecture whose proof implies the proof of Collatz conjecture by using proposed Collatz tree. © 2019 IEEE.

关键词： Number theory

来源：评论

学校读者我要写书评

暂无评论

Efficient differentiated storage architecture for large-scale flow tables in openflow networks 21

Efficient differentiated storage architecture for large-scal...

引用

作者： Xiong, Bing Wu, Rengeng Liao, Zhuofan Wang, Jin School of Computer AND Communication Engineering Changsha University of Science AND Technology Changsha410114 China Department of Computer and Information Sciences Temple University Philadelphia19122 United States Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science AND Technology Changsha China

ISBN: (纸本)9781728120584

As a novel network paradigm, Software Defined Networking (SDN) decouples control logic functions from data forwarding devices, and introduces a separate control plane to manipulate underlying switches via southbound interfaces like OpenFlow. However, it leads to large-scale flow tables and poses serious challenges on their storage resources and lookup performance in OpenFlow switches. This paper is thus motivated to propose an efficient differentiated storage architecture for large-scale flow tables in OpenFlow networks. Firstly, we investigate into the impact of wildcards in match fields on packet-in-batch property within a flow based on network traffic locality. Then, packet flows are dynamically distinguished into active ones and idle ones in terms of their short-term states. Subsequently, we store the match fields of active flows and idle flows respectively in TCAM and SRAM, and the content fields of both types of flows in DRAM, to effectively relieve the insufficiency of TCAM capacity. Finally, we evaluate the performance of our proposed flow table storage architecture with real network traffic traces by experiments. The experimental results indicate that our proposed storage architecture obviously outperforms the traditional one applying the elephant/mice flow differentiation method in terms of TCAM hit rates and average flow table access time. © 2019 IEEE.

关键词： Software defined networking

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：