检索结果-内蒙古大学图书馆

International Conference on computer vision and Graphics, ICCVG 2022

作者： Przewlocka-Rus, Dominika Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC—performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

rafPS:A shapley-based visual analytics approach to interpret traffic

引用

Computational Visual Media 2024年第6期10卷 1101-1119页

作者： Zezheng Feng Yifan Jiang Hongjun Wang Zipei Fan Yuxin Ma Shuang-Hua Yang Huamin Qu Xuan Song Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 18055China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong KongChina Department of Computer Science University of ReadingBerkshire RG66AHUK Center for Spatial Information Science the University of TokyoTokyo 113-00331Japan Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet Southern University of Science and TechnologyShenzhen 518055China

Recent achievements in deep learning(DL)have demonstrated its potential in predicting traffic *** predictions are beneficial for understanding the situation and making traffic control ***,most state-of-the-art DL models are consi-dered“black boxes”with little to no transparency of the underlying mechanisms for end *** previous studies attempted to“open the black box”and increase the interpretability of generated ***,handling complex models on large-scale spatiotemporal data and discovering salient spatial and temporal patterns that significantly influence traffic flow remain *** overcome these challenges,we present TrafPS,a visual analytics approach for interpreting traffic prediction outcomes to support decision-making in traffic management and urban *** measurements region SHAP and trajectory SHAP are proposed to quantify the impact of flow patterns on urban traffic at different *** on the task requirements from domain experts,we employed an interactive visual interface for the multi-aspect exploration and analysis of significant flow *** real-world case studies demonstrate the effectiveness of TrafPS in identifying key routes and providing decision-making support for urban planning.

关键词： data visualization model interpretation urban planning urban visual analytics

来源：评论

学校读者我要写书评

暂无评论

Multi-label Textual Data Augmentation Using BERT Based on Transformer Model 1

引用

13th International Conference on Information Systems and Advanced Technologies, ICISAT 2023

作者： Rouabhi, Roumaissa Hammami, Nacer Eddine Azizi, Nabiha Benzebouchi, Nacer Eddine Chaib, Rim LabGed Laboratory Badji Mokhtar University Annaba Algeria Computer Engineering Department College of Engineering and Computer Science Mustaqbal University Buraydah Saudi Arabia

ISBN: (数字)9783031605918

ISBN: (纸本)9783031605901

In recent years, the healthcare field has taken a turn towards the AI domain, with applications such as image segmentation and medical report classification leading researchers to delve deeper into this area. On the other hand, the natural language processing has taken another turn with the arrival of the transformer models, the deep learning pre-trained models on a large corpus of documents, permitting an optimal use of medical text documents. However, the lack of diversification in text data more specifically multilabel data can be a constraint to get performant results. In this study, we are utilizing BioBERT for multilabel text classification, with the aim of achieving more refined results by implementing a data augmentation approach using a BERT-based transformer model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 6073-6087页

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Zhou, Huiyu Felsberg, Michael Tao, Dacheng Li, Xuelong University of York Department of Computer Science United Kingdom University of Leicester School of Computing and Mathematical Sciences United Kingdom Linkoping University Computer Vision Laboratory Sweden Nanyang Technological University College of Computing & Data Science Singapore China Northwestern Polytechnical University Key Laboratory of Intelligent Interaction and Applications Ministry of Industry and Information Technology Xi'an China

Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining coherence between known and unknown (missing) regions. This issue arises from the lack of explicit spatial and semantic alignment during the diffusion process, resulting in content that does not smoothly integrate with the original image. Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts. In this work, we propose ConFill, a novel framework that introduces a Context-Adaptive Discrepancy (CAD) model to ensure that intermediate distributions of known and unknown regions are closely aligned throughout the diffusion process. By incorporating CAD, our model progressively reduces discrepancies between generated and original images at each diffusion step, leading to contextually aligned completion. Moreover, ConFill uses a new Dynamic Sampling mechanism that adaptively increases the sampling rate in regions with high reconstruction complexity. This approach enables precise adjustments, enhancing detail and integration in restored areas. Extensive experiments demonstrate that ConFill outperforms current methods, setting a new benchmark in image completion. © 1979-2012 IEEE.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

A multi-feature-based intelligent redundancy elimination scheme for cloud-assisted health systems

引用

CAAI Transactions on Intelligence Technology 2024年第2期9卷 491-510页

作者： Ling Xiao Beiji Zou Xiaoyan Kui Chengzhang Zhu Wensheng Zhang Xuebing Yang Bob Zhang School of Computer Science and Engineering Central South UniversityChangshaChina Hunan Engineering Research Center of Machine Vision and Intelligent Medicine Central South UniversityChangshaChina The College of Literature and Journalism Central South UniversityChangshaChina Institute of Automation Chinese Academy of SciencesBeijingChina Department of Computer and Information Science University of MacaoMacaoChina

Redundancy elimination techniques are extensively investigated to reduce storage overheads for cloud-assisted health *** eliminates the redundancy of duplicate blocks by storing one physical instance referenced by multiple *** compression is usually regarded as a complementary technique to deduplication to further remove the redundancy of similar blocks,but our observations indicate that this is disobedient when data have sparse duplicate *** addition,there are many overlapped deltas in the resemblance detection process of post-deduplication delta compression,which hinders the efficiency of delta compression and the index phase of resemblance detection inquires abundant non-similar blocks,resulting in inefficient system ***,a multi-feature-based redundancy elimination scheme,called MFRE,is proposed to solve these *** similarity feature and temporal locality feature are excavated to assist redundancy elimination where the similarity feature well expresses the duplicate ***,similarity-based dynamic post-deduplication delta compression and temporal locality-based dynamic delta compression discover more similar base blocks to minimise overlapped deltas and improve compression ***,the clustering method based on block-relationship and the feature index strategy based on bloom filters reduce IO overheads and improve system *** demonstrate that the proposed method,compared to the state-of-the-art method,improves the compression ratio and system throughput by 9.68%and 50%,respectively.

关键词： big data cloud computing compression data compression medical applications performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Classification Using Deep and Quantum Neural Networks

Traffic Sign Classification Using Deep and Quantum Neural Ne...

引用

International Conference on computer vision and Graphics, ICCVG 2022

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using a hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate that currently QNN do not outperform classical DCNN (Deep Convolutuional Neural Networks), yet still provide an accuracy of over 90% and are a definitely promising solution for advanced computer vision. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Network of Groupwise Separable Convolution and vision Transformer for Hyperspectral Image Classification 3

A Lightweight Network of Groupwise Separable Convolution and...

引用

3rd International Conference on Optics and Machine vision, ICOMV 2024

作者： Zhao, Zhuoyi Xu, Xiang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China The Artificial Intelligence and Computer Vision Laboratory University of Electronic Science and Technology of China Zhongshan Institute Zhongshan China

ISBN: (纸本)9781510680319

Hyperspectral image (HSI) data consists of images with numerous contiguous spectral bands and promotes the extensive applications in the field of remote sensing. Recent approaches based on vision Transformer (ViT) have achieved remarkable performance in HSI classification tasks due to their ability to extract global spatial features and model long-range dependencies. However, ViT has complex network structure, training is challenging and lacks adequate consideration of local spatial and spectral receptive fields in hyperspectral data. To solve the problems above, we propose a lightweight network model known as the Groupwise Separable Convolution and vision Transformer (GSCViT). Firstly, we introduce a parameter-free attention for spectral calibration (SC). Then, we meticulously design a novel convolutional approach named Groupwise Separable Convolution (GSC), which greatly reduce the number of convolutional kernel parameters and effectively capture local spatial-spectral information in HSI data. In addition, we employ Groupwise Separable Multi-Head Self-Attention (GSSA) to replace the traditional Multi-Head Self-Attention (MSA) in ViT, thus can simultaneously attend to local and global spatial features in HSI with lower computational burden. Experiments on two benchmark HSI datasets demonstrate that our GSCViT model achieves excellent accuracy with relatively small training samples and outperforms some existing HSI classification algorithms. © 2024 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A high speed dynamic comparator with automatic offset compensation

A high speed dynamic comparator with automatic offset compen...

引用

2024 Panhellenic Conference on Electronics and Telecommunications, PACET 2024

作者： Tsirmpas, George Kontelis, Spyros Souliotis, George Plessas, Fotis University of Patras Electronics Laboratory Physics Department Patras Greece University of Peloponnese Department of Electrical and Computer Engineering Greece University of Thessaly Department of Electrical and Computer Engineering Volos Greece

ISBN: (纸本)9798350318845

A high-speed dynamic comparator with automatic dc offset compensation is proposed in this paper. The comparator is based on a double-tail topology and reduces the dc offset by a calibration circuit. Avoiding using the commonly used capacitive calibration, it can operate at a higher speed compared to other topologies. Designed in a CMOS 65nm technology node, it operates with 1 V supply voltage and clock speed at 10 GHz. © 2024 IEEE.

关键词： Comparators (optical)

来源：评论

学校读者我要写书评

暂无评论

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

引用

Acta Oceanologica Sinica 2024年第7期43卷 26-39页

作者： Feng Nan Zhuolin Li Jie Yu Suixiang Shi Xinrong Wu Lingyu Xu Department of Computer Engineering and Science Shanghai UniversityShanghai 200444China Key Laboratory of Digital Ocean National Marine Data and Information ServiceTianjin 300171China

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related ***,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean *** graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among *** this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior *** and spatial dependencies in the time series were then captured using temporal and graph *** also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid *** this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea *** compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

关键词： dynamic associations three-dimensional ocean temperature prediction graph neural network time series gridded data

来源：评论

学校读者我要写书评

暂无评论

Design of surrogate models in civil engineering by neural networks 9

Design of surrogate models in civil engineering by neural ne...

引用

9th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2024

作者： Drahy, Vojtech Marik, Radek Kalviainen, Heikki Czech Technical University in Prague Department of Computer Science Prague Czech Republic Czech Technical University in Prague Department of Telecommunication Engineering Prague Czech Republic Lappeenranta-Lahti University of Technology Lut Computer Vision and Pattern Recognition Laboratory Lappeenranta Finland

ISBN: (纸本)9798350342482

We present a task from the critical infrastructure field in materials engineering. We created a surrogate model for the bridge construction object to determine the material parameters' values. The work aims to use neural networks to conduct an initial investigation of the task and to find out the aspects of machine learning application. To reduce the computational complexity of the models, we designed specific neural networks whose architecture corresponds to the structure and characteristics of the processed data. Furthermore, we outcome also interpretability and justification of the model's decision-making. The main contribution of the work is the replacement of the unknown or too complex physical, mathematical description of material objects with a neural network model. © 2024 IEEE.

关键词： Neural network models

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：