检索结果-南通市图书馆

AFBNet: A Lightweight Adaptive Feature Fusion Module for Super-Resolution Algorithms

Computer Modeling in Engineering & Sciences 2024年第9期140卷 2315-2347页

作者： Lirong Yin Lei Wang Siyu Lu Ruiyang Wang Haitao Ren ahmed alsanad Salman A.AlQahtani Zhengtong Yin Xiaolu Li Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia College of Resource and Environment Engineering Guizhou UniversityGuiyang550025China School of Geographical Sciences Southwest UniversityChongqing400715China

At present,super-resolution algorithms are employed to tackle the challenge of low image resolution,but it is difficult to extract differentiated feature details based on various inputs,resulting in poor generalization *** this situation,this study first analyzes the features of some feature extraction modules of the current super-resolution algorithm and then proposes an adaptive feature fusion block(AFB)for feature *** module mainly comprises dynamic convolution,attention mechanism,and pixel-based gating *** with dynamic convolution with scale information,the network can extract more differentiated feature *** introduction of a channel spatial attention mechanism combined with multi-feature fusion further enables the network to retain more important feature *** convolution and pixel-based gating mechanisms enhance the module’s ***,a comparative experiment of a super-resolution algorithm based on the AFB module is designed to substantiate the efficiency of the AFB *** results revealed that the network combined with the AFB module has stronger generalization ability and expression ability.

关键词： Super-resolution feature extraction dynamic convolution attention mechanism gate control

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

DPAL-BERT:A Faster and Lighter Question Answering Model

引用

Computer Modeling in Engineering & Sciences 2024年第10期141卷 771-786页

作者： Lirong Yin Lei Wang Zhuohang Cai Siyu Lu Ruiyang Wang ahmed alsanad Salman A.AlQahtani Xiaobing Chen Zhengtong Yin Xiaolu Li Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA 70803USA School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA 70803USA College of Resources and Environmental Engineering Guizhou UniversityGuiyang550025China School of Geographical Sciences Southwest UniversityChongqing400715China

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering ***,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced *** study aims to minimize the inference time of such models while maintaining computational *** also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and *** research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge *** experimental results showed that the distilled models greatly outperform models trained from *** addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the *** demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

关键词： DPAL-BERT question answering systems knowledge distillation model compression BERT Bi-directional long short-term memory(BiLSTM) knowledge information transfer PAL-BERT training efficiency natural language processing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Convolution-Transformer for Image Feature Extraction

引用

Computer Modeling in Engineering & Sciences 2024年第10期141卷 87-106页

作者： Lirong Yin Lei Wang Siyu Lu Ruiyang Wang Youshuai Yang Bo Yang Shan Liu ahmed alsanad Salman A.AlQahtani Zhengtong Yin Xiaolu Li Xiaobing Chen Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia College of Resources and Environmental Engineering Key Laboratory of Karst Georesources and Environment(Guizhou University)Ministry of EducationGuiyang550025China School of Geographical Sciences Southwest UniversityChongqing400715China School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA70803USA

This study addresses the limitations of Transformer models in image feature extraction,particularly their lack of inductive bias for visual *** to Convolutional Neural Networks(CNNs),the Transformers are more sensitive to different hyperparameters of optimizers,which leads to a lack of stability and slow *** tackle these challenges,we propose the Convolution-based Efficient Transformer Image Feature Extraction Network(CEFormer)as an enhancement of the Transformer *** model incorporates E-Attention,depthwise separable convolution,and dilated convolution to introduce crucial inductive biases,such as translation invariance,locality,and scale invariance,into the Transformer ***,we implement a lightweight convolution module to process the input images,resulting in faster convergence and improved *** results in an efficient convolution combined Transformer image feature extraction *** results on the ImageNet1k Top-1 dataset demonstrate that the proposed network achieves better accuracy while maintaining high computational *** achieves up to 85.0%accuracy across various model sizes on image classification,outperforming various baseline *** integrated into the Mask Region-ConvolutionalNeuralNetwork(R-CNN)framework as a backbone network,CEFormer outperforms other models and achieves the highest mean Average Precision(mAP)*** research presents a significant advancement in Transformer-based image feature extraction,balancing performance and computational efficiency.

关键词： Transformer E-Attention depth convolution dilated convolution CEFormer

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

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：