检索结果-内蒙古大学图书馆

reb-DINO: A Lightweight Pedestrian Detection Model With Structural re-parameterization in Apple Orchard

COMPUTATIONAL INTELLIGENCE 2025年第2期41卷

作者： Li, Ruiyang Song, Ge Wang, Shansong Zeng, Qingtian Yuan, Guiyuan Ni, Weijian Xie, Nengfu Xiao, Fengjin Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao Peoples R China Shandong Univ Sci & Technol Coll Elect & Informat Engn Qingdao Peoples R China Agr Informat Inst CAAS Beijing Peoples R China Natl Climate Ctr Beijing Peoples R China

Pedestrian detection is crucial in agricultural environments to ensure the safe operation of intelligent machinery. In orchards, pedestrians exhibit unpredictable behavior and can pose significant challenges to navigation and operation. This demands reliable detection technologies that ensures safety while addressing the unique challenges of orchard environments, such as dense foliage, uneven terrain, and varying lighting conditions. To address this, we propose reB-DINO, a robust and accurate orchard pedestrian detection model based on an improved DINO. Initially, we improve the feature extraction module of DINO using structural re-parameterization, enhancing accuracy and speed of the model during training and inference decoupling. In addition, a progressive feature fusion module is employed to fuse the extracted features and improve model accuracy. Finally, the network incorporates a convolutional block attention mechanism and an improved loss function to improve pedestrian detection rates. The experimental results demonstrate a 1.6% improvement in recall on the NreC dataset compared to the baseline. Moreover, the results show a 4.2% improvement in mAP$$ \mathrm{mAP} $$ and the number of parameters decreases by 40.2% compared to the original DINO. In the PiFO dataset, the mAP$$ \mathrm{mAP} $$ with a threshold of 0.5 reaches 99.4%, demonstrating high detection accuracy in realistic scenarios. Therefore, our model enhances both detection accuracy and real-time object detection capabilities in apple orchards, maintaining a lightweight attributes, surpassing mainstream object detection models.

关键词： agriculture lightweight object detection pedestrian detection re-parameterization

来源：评论

学校读者我要写书评

暂无评论

An efficient re-parameterization feature pyramid network on YOLOv8 to the detection of steel surface defect

引用

NEUROCOMPUTING 2025年 614卷

作者： Xie, Weining Ma, Weifeng Sun, Xiaoyong Zhejiang Univ Sci & Technol Sch Informat & Elect Engn 318 Liuhe Rd Hangzhou 310023 Zhejiang Peoples R China

In the field of steel production, the detection of steel surface defects is one of the most important guarantees for the quality of steel production. In the process of defect detection, there are problems regarding the noise of the acquisition background, the scale of defects, and the detection speed. At present, in the face of complex steel surface defects, realizing efficient real-time steel surface defect detection has become a difficult problem. In this paper, we propose a lightweight and efficient real-time defect detection method, LDE-YOLO, based on YOLOv8. First, we propose a lightweight multi-scale feature extraction module, LighterMSMC, which not only achieves a lightweight backbone network, but also effectively guarantees the long range dependence of the features, so as to realize multi-scale feature extraction more efficiently. Secondly, we propose lightweight re-parameterized feature pyramid, DE-FPN, in which the sparse patterns of the overall features and the detailed features of the local features are efficiently captured by the DE-Block, and then efficiently fused by the PAN feature fusion structure. Finally, we propose Efficient Head, which lightens the model by group convolution while its improves the diagonal correlation of the feature maps on some specific datasets, thus enhancing the detection performance. Our proposed LDE-YOLO obtains 80.8 mAP and 75.5 FPS on NEU-DET , 80.5 mAP and 75.5 FPS on GC10-DET. It obtains 2.5 mAP and 4.7 mAP enhancement compared to the baseline model, and the detection speed is also improved by 10.4 FPS, while in terms of the number of floating point operations and parameters of the model reduced by 60.2% and 49.1%, which is sufficient to illustrate its lightweight effectiveness and realize an efficient real-time steel surface defect detection model.

关键词： Defect detection re-parameterization Feature fusion YOLOv8

来源：评论

学校读者我要写书评

暂无评论

re-parameterization reduces irreducible geometric constraint systems

引用

COMPUTER-AIDED DESIGN 2016年 70卷 182-192页

作者： Barki, Hichem Fang, Lincong Michelucci, Dominique Foufou, Sebti Qatar Univ Coll Engn CSE Dept Doha Qatar Zhejiang Univ Finance & Econ Sch Informat Technol Hangzhou 310018 Zhejiang Peoples R China Univ Bourgogne Franche Comte Arts & Metiers CNRS LE21 UMR6306 F-21000 Dijon France

You recklessly told your boss that solving a non-linear system of size n (n unknowns and n equations) requires a time proportional to n, as you were not very attentive during algorithmic complexity lectures. So now, you have only one night to solve a problem of big size (e.g., 1000 equations/unknowns), otherwise you will be fired in the next morning. The system is well-constrained and structurally irreducible: it does not contain any strictly smaller well-constrained subsystems. Its size is big, so the Newton Raphson method is too slow and impractical. The most frustrating thing is that if you knew the values of a small number k << n of key unknowns, then the system would be reducible to small square subsystems and easily solved. You wonder if it would be possible to exploit this reducibility, even without knowing the values of these few key unknowns. This article shows that it is indeed possible. This is done at the lowest level, at the linear algebra routines level, so that numerous solvers (Newton Raphson, homotopy, and also p-adic methods relying on Hensel lifting) widely involved in geometric constraint solving and CAD applications can benefit from this decomposition with minor modifications. For instance, with k << n key unknowns, the cost of a Newton iteration becomes O(kn(2)) instead of O(n(3)). Several experiments showing a significant performance gain of our re-parameterization technique are reported in this paper to consolidate our theoretical findings and to motivate its practical usage for bigger systems. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Geometric constraints solving Geometric modeling with constraints re-parameterization reduction Decomposition

来源：评论

学校读者我要写书评

暂无评论

re-parameterization Making GC-Net-Style 3DConvNets More Efficient 16th

Re-parameterization Making GC-Net-Style 3DConvNets More Effi...

引用

16th Asian Conference on Computer Vision (ACCV)

作者： Endo, Takeshi Kaji, Seigo Matono, Haruki Takemura, Masayuki Shima, Takeshi Hitachi Ltd Res & Dev Grp Chiyoda City Japan Hitachi Astemo Ltd Sunnyvale CA USA

ISBN: (纸本)9783031263187;9783031263194

For depth estimation using a stereo pair, deep learning methods using 3D convolution have been proposed. While the estimation accuracy is high, 3D convolutions on cost volumes are computationally expensive. Hence, we propose a method to reduce the computational cost of 3D convolution-based disparity networks. We apply kernel re-parameterization, which is used for constructing efficient backbones, to disparity estimation. We convert learned parameters, and these values are used for inference to reduce the computational cost of filtering cost volumes. Experimental results on the KITTI 2015 dataset show that our method can reduce the computational cost by 31-61% from those of trained models without any performance loss. Our method can be used for any disparity network that uses 3D convolution for cost volume filtering.

关键词： Stereo matching re-parameterization Efficient architecture

来源：评论

学校读者我要写书评

暂无评论

repDNet:A re-parameterization despeckling network for autonomous underwater side-scan sonar imaging with prior-knowledge customized convolution

引用

Defence Technology（防务技术） 2024年第5期35卷 259-274页

作者： Zhuoyi Li Zhisen Wang Deshan Chen Tsz Leung Yip Angelo P.Teixeira Department of Logistics and Maritime Studies The Hong Kong Polytechnic UniversityChina State Key Laboratory of Maritime Technology and Safety Wuhan University of TechnologyChina School of Transportation and Logistics Engineering Wuhan University of TechnologyChina National Engineering Research Center for Water Transport Safety Wuhan University of TechnologyChina Centre for Marine Technology and Ocean Engineering(CENTEC) Instituto Superior TecnicoUniversidade de LisboaPortugal

Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging along a predetermined ***,SSS images often suffer from speckle noise caused by mutual interference between echoes,and limited AUV computational resources further hinder noise *** approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain *** address the problem,rep DNet,a novel and effective despeckling convolutional neural network is *** DNet introduces two re-parameterized blocks:the Pixel Smoothing Block(PSB)and Edge Enhancement Block(EEB),preserving edge information while attenuating speckle *** training,PSB and EEB manifest as double-layered multi-branch structures,integrating first-order and secondorder derivatives and smoothing *** inference,the branches are re-parameterized into a 3×3 convolution,enabling efficient inference without sacrificing *** DNet comprises three computational operations:3×3 convolution,element-wise summation and rectified Linear Unit *** on benchmark datasets,a real SSS dataset and Data collected at Lake Mulan aestablish rep DNet as a well-balanced network,meeting the AUV computational constraints in terms of performance and latency.

关键词： Side-scan sonar Sonar image despeckling Domain knowledge re-parameterization

来源：评论

学校读者我要写书评

暂无评论

Edge-priority-extraction network using re-parameterization for real-time super-resolution

引用

VISUAL COMPUTER 2024年第11期40卷 7623-7636页

作者： Ying, Wen-yuan Dong, Tian-yang Fan, Jing Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou Peoples R China

recently, super-resolution (SR) has achieved superior performance with the development of deep learning. However, previous methods usually require considerable computational resources with a large model size, which hinders practical applications. To achieve real-time inference and high quality for SR, this paper presents an edge-priority-extraction network, which is constructed with our proposed edge-priority blocks (EPB). The EPB utilizes multiple branches with edge information to further improve the network representation. Moreover, it can be re-parameterized for efficient inference. For more effective utilization of edge information, this paper also proposes the mix-priority filter with edge extraction of horizontal and vertical priorities to improve the network performance. The filters can adaptively extract the edge information with multi-direction derivatives. The experimental results show that our models can use less computational cost to meet the real-time demand and have a better SR performance than the recent real-time SR models.

关键词： Super-resolution real-time inference Edge information re-parameterization

来源：评论

学校读者我要写书评

暂无评论

Hierarchical U-net with re-parameterization technique for spatio-temporal weather forecasting

引用

MACHINE LEARNING 2024年第6期113卷 3399-3417页

作者： Xu, Baowen Wang, Xuelei Li, Jingwei Liu, Chengbao Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

Due to the considerable computational demands of physics-based numerical weather prediction, especially when modeling fine-grained spatio-temporal atmospheric phenomena, deep learning methods offer an advantageous approach by leveraging specialized computing devices to accelerate training and significantly reduce computational costs. Consequently, the application of deep learning methods has presented a novel solution in the field of weather forecasting. In this context, we introduce a groundbreaking deep learning-based weather prediction architecture known as Hierarchical U-Net (HU-Net) with re-parameterization techniques. The HU-Net comprises two essential components: a feature extraction module and a U-Net module with re-parameterization techniques. The feature extraction module consists of two branches. First, the global pattern extraction employs adaptive Fourier neural operators and self-attention, well-known for capturing long-term dependencies in the data. Second, the local pattern extraction utilizes convolution operations as fundamental building blocks, highly proficient in modeling local correlations. Moreover, a feature fusion block dynamically combines dual-scale information. The U-Net module adopts repBlock with re-parameterization techniques as the fundamental building block, enabling efficient and rapid inference. In extensive experiments carried out on the large-scale weather benchmark dataset WeatherBench at a resolution of 1.40625 degrees, the results demonstrate that our proposed HU-Net outperforms other baseline models in both prediction accuracy and inference time.

关键词： Spatio-temporal weather forecasting U-Net re-parameterization

来源：评论

学校读者我要写书评

暂无评论

Texture-Enhanced Framework by Differential Filter-Based re-parameterization for Super-resolution on PC/Mobile

引用

NEURAL PROCESSING LETTERS 2023年第9期55卷 12183-12203页

作者： Liu, Yongxu Fu, Xiaoyan Zhou, Lijuan Li, ChuanZhong Capital Normal Univ Coll Informat Engn Beijing 100089 Peoples R China Hainan Univ Sch Cryptol Sch Cyberspace Secur Haikou 570228 Hainan Peoples R China

In this paper, we aim to improve the imaging quality of super-resolution (SR) without increasing the inference time to address the difficulty of trading off between quality and inference time in many existing methods and design a deployment-friendly, lightweight model for mobile devices. Specifically, we propose a general repDFSR framework to enhance the textures of SR images while avoiding additional inference time overhead, which can be applied to existing SR networks. It incorporates innovative convolutional block design, loss function design, and the re-parameterizable technique. In repDFSR, we propose a re-parameterizable texture-enhanced convolution based on differential filters. It extracts texture information more advantageous and efficient in training than regular convolution. Secondly, we propose a DF loss function to compel the model to super-resolve the gradient mappings with high variance, thus reconstructing images with sharper textures. Moreover, we propose a TELNet network for mobile devices based on the repDFSR framework to validate the effectiveness of repDFSR and our thoughts on practical applications of SR on mobile devices. The experimental results demonstrate the successful integration of the repDFSR framework with the existing SR methods. Additionally, the TELNet meets the requirements of mobile devices for hardware and quantization limitations, showcasing superior SR performance compared to classic and state-of-the-art methods.

关键词： Image super-resolution re-parameterization Differential filter Lightweight network

来源：评论

学校读者我要写书评

暂无评论

Texture-aware re-parameterization to mitigate accuracy drop after quantization for 4K/8K image super-resolution

引用

VISUAL COMPUTER 2024年第8期40卷 5533-5544页

作者： Liu, Yongxu Fu, Xiaoyan Sun, Zhong Capital Normal Univ Coll Informat Engn Beijing 100089 Peoples R China

In this paper, we aim to improve super-resolution (SR) imaging quality on 4K/8K images with a negligible increase in computational cost and alleviate the accuracy drop after quantization. Experiments have discovered two phenomena: (1) the re-parameterization (rep) technique has no apparent advantages in regions with smooth textures, and (2) the accuracy drop after quantization compared with SR methods based on No-rep because the structure information of the image will be weakened caused by the multi-branch fusion in rep technique. Inspired by the above phenomenon, we innovatively combine texture classification and rep techniques to propose a generic TArepSR framework (consisting of TA-Module and VarrepSR-Module) to adjust the branching of rep blocks texture-awarely. Specifically, the TA-Module is a lightweight classification network to classify textures in different regions. An existing SR network using texture-aware rep techniques can be used as the VarrepSR-Module to super-resolute images with higher imaging quality without additional computational costs. Moreover, we propose a TC loss to avoid over-fitting caused by an unbalanced degree of the tendency of classification results to classify different textures better. Experiments show that our TArepSR can not only improve the imaging quality of most existing methods (e.g., FSRCNN, CARN, EDSR, XLSR) on 4K/8K images with negligible increase in computational cost but also improve the accuracy after quantization compared with the state-of-the-art rep methods.

关键词： Super-resolution re-parameterization Model quantization

来源：评论

学校读者我要写书评

暂无评论

A new method to improve estimation of uncertain parameters in the Ensemble Kalman filter by re-parameterization employing prior statistics correction

引用

JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING 2015年第Part1期27卷 247-259页

作者： Bagherinezhad, Abolfazl Pishvaie, Mahmoud reza Boozarjomehry, Ramin Bozorgmehry Sharif Univ Technol Dept Chem & Petr Engn Tehran Iran

The Ensemble Kalman Filter (EnKF) is a Monte Carlo based method to assimilate the measurement data sequentially in time. Although, EnKF has some advantages over the other Kalman based methods to deal with non-linear and/or high dimensional reservoir models, it also suffers from deficiency in estimation of non-Gaussian parameters. In this work, we propose a re-parameterization method to handle non-Gaussian parameters via Ensemble Kalman Filter framework. For this purpose, concept of cumulative distribution function transformation has been used. In addition, the statistics of prior information have been aggregated in the state vector in order to capture the prior uncertainties of non-Gaussian parameters. To evaluate the performance of the new method, three estimation examples have been implemented. These examples are designed to evaluate the performance of the proposed method to estimate both local and global parameters. The performance of method in handling non-Gaussian prior as well as capturing the prior uncertainty has been assessed. The results revealed that, the proposed method handled both non-Gaussian prior and capturing of the prior uncertainties of the local and global parameters quite efficiently. Compared to previously conducted researches, new algorithm would considerably reduce the number of required ensemble members to converge to the appropriate solution. Standard ensemble Kalman filter and normal score transformation have been also implemented for each setup;the obtained results show that the new proposed method outperforms the other alternate methods. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Ensemble Kalman filter Uncertain prior Non-Gaussian Prior statistics re-parameterization Parameter estimation

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：