检索结果-南通市图书馆

Ultra-lightweight CNN design based on neural architecture search and knowledge distillation: A novel method to build the automatic recognition model of space target ISAR images

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2022年第6期18卷 1073-1095页

作者： Hong Yang Ya-sheng Zhang Can-bin Yin Wen-zhe Ding Space Engineering University Beijing101416China Beijing Institute of Tracking and Telecommunications Technology China

In this paper,a novel method of ultra-lightweight convolution neural network(CNN)design based on neural architecture search(NAS)and knowledge distillation(KD)is *** can realize the automatic construction of the space target inverse synthetic aperture radar(ISAR)image recognition model with ultra-lightweight and high *** method introduces the NAS method into the radar image recognition for the first time,which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model(STIIARM).On this basis,the NAS model’s knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure(FSP)distillation ***,the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided,and the ultralightweight STIIARM can be *** the method,the Inverted Linear Bottleneck(ILB)and Inverted Residual Block(IRB)are firstly taken as each block’s basic structure in *** the expansion ratio,output filter size,number of IRBs,and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search ***,the recognition accuracy and computational complexity are taken as the objective function and constraint conditions,respectively,and the global optimization model of the CNN architecture search is ***,the simulated annealing(SA)algorithm is used as the search strategy to search out the lightweight and high accuracy STIIARM *** that,based on the three principles of similar block structure,the same corresponding channel number,and the minimum computational complexity,the more lightweight student model is designed,and the FSP matrix pairing between the NAS model and student model is ***,by minimizing the loss between the FSP matrix pairs of the NAS model and student model,the student model’s weight adjust

关键词： Space target ISAR image Neural architecture search Knowledge distillation lightweight model

Using an improved lightweight YOLOv8 model for real-time detection of multi-stage apple fruit in complex orchard environments

在线全文

学校读者我要写书评

暂无评论

Artificial Intelligence in Agriculture 2024年第1期11卷 70-82页

作者： Baoling Ma Zhixin Hua Yuchen Wen Hongxing Deng Yongjie Zhao Liuru Pu Huaibo Song College of Mechanical and Electronic Engineering Northwest A&F UniversityYanglingShaanxi 712100China Key Laboratory of Agricultural Internet of Things Ministry of Agricultureand Rural AffairsYanglingShaanxi 712100China Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Services YanglingShaanxi 712100China

For the purpose of monitoring apple fruits effectively throughout the entire growth period in smart orchards.A lightweight model named YOLOv8n-ShuffleNetv2-Ghost-SE was *** ShuffleNetv2 basic modules and down-sampling modules were alternately connected,replacing the Backbone of YOLOv8n *** Ghost modules replaced the Conv modules and the C2fGhost modules replaced the C2f modules in the Neck part of the ***2 reduced the memory access cost through channel splitting *** Ghost module combined linear and non-linear convolutions to reduce the network computation *** Wise-IoU(WIoU)replaced the CIoU for calculating the bounding box regression loss,which dynamically adjusted the anchor box quality threshold and gradient gain allocation strategy,optimizing the size and position of predicted bounding *** Squeeze-and-Excitation(SE)was embedded in the Backbone and Neck part of YOLOv8n to enhance the representation ability of feature *** algorithm ensured high precision while having small model size and fast detection speed,which facilitated model migration and *** 9652 images validated the effectiveness of the *** YOLOv8n-ShuffleNetv2-Ghost-SE model achieved Precision of 94.1%,Recall of 82.6%,mean Average Precision of 91.4%,model size of 2.6 MB,parameters of 1.18 M,FLOPs of 3.9 G,and detection speed of 39.37 *** detection speeds on the Jetson Xavier NX development board were 3.17 *** with advanced models including Faster R-CNN,SSD,YOLOv5s,YOLOv7‑tiny,YOLOv8s,YOLOv8n,MobileNetv3_small-Faster,MobileNetv3_small-Ghost,ShuflleNetv2-Faster,ShuflleNetv2-Ghost,ShuflleNetv2-Ghost-CBAM,ShuflleNetv2-Ghost-ECA,and ShuflleNetv2-Ghost-CA demonstrated that the method achieved smaller model and faster detection *** research can provide reference for the development of smart devices in apple orchards.

关键词： Multi-stage apple fruit Deep learning Real-time detection lightweight model

Multi-perception large kernel convnet for efficient image super-resolution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

四川大学学报(自然科学版) 2025年第1期62卷 67-78页

作者： MIAO Xuan LI Zheng XU Wen-Zheng College of Computer Science(College of Software) Sichuan UniversityChengdu 610065China Tianfu Engineering-Oriented Numerical Simulation&Software Innovation Center Sichuan UniversityChengdu 610207China

Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art *** efforts have explored the incorporation of Transformers to augment network performance in ***,the high computational cost of Transformers makes them less suitable for deployment on lightweight ***,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel *** this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel ***,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these *** addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel *** results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.

关键词： Single Image Super-Resolution lightweight model Deep learning Large kernel

同方期刊数据库

Target localization method of non-cooperative spacecraft on on-orbit service

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第11期35卷 336-348页

作者： Yingxiao LI Ju HUO Ping MA Ruiye JIANG Control and Simulation Center Harbin Institute of TechnologyHarbin 150001 China

With the explosion of the number of meteoroid/orbital debris in terrestrial space in recent years, the detection environment of spacecraft becomes more complex. This phenomenon causes most current detection methods based on machine learning intractable to break through the two difficulties of solving scale transformation problem of the targets in image and accelerating detection rate of high-resolution images. To overcome the two challenges, we propose a novel noncooperative target detection method using the framework of deep convolutional neural ***, a specific spacecraft simulation dataset using over one thousand images to train and test our detection model is built. The deep separable convolution structure is applied and combined with the residual network module to improve the network’s backbone. To count the different shapes of the spacecrafts in the dataset, a particular prior-box generation method based on K-means cluster algorithm is designed for each detection head with different scales. Finally, a comprehensive loss function is presented considering category confidence, box parameters, as well as box confidence. The experimental results verify that the proposed method has strong robustness against varying degrees of luminance change, and can suppress the interference caused by Gaussian noise and background complexity. The mean accuracy precision of our proposed method reaches 93.28%, and the global loss value is 13.252. The comparative experiment results show that under the same epoch and batchsize, the speed of our method is compressed by about 20% in comparison of YOLOv3, the detection accuracy is increased by about 12%, and the size of the model is reduced by nearly 50%.

关键词： Spacecraft service High resolution image Object detection Complex environment lightweight model

MobileNet-Based IoT Malware Detection with Opcode Features

在线全文

学校读者我要写书评

暂无评论

Journal of Communications and Information Networks 2023年第3期8卷 221-230页

作者： Changren Mai Riqing Liao Jing Ren Yuanxiang Gong Kaibo Zhang Chiya Zhang Harbin Institute of Technology Shenzhen 518055China University of Electronic Science and Technology of China Chengdu 611731China

In recent years,with the rapid development of Internet and hardware technologies,the number of Internet of things(IoT)devices has grown ***,IoT devices are constrained by power consumption,making the security of IoT *** such as Botnets and Worms poses significant security threats to users and enterprises *** learning models have demonstrated strong performance in various tasks across different domains,leading to their application in malicious software ***,due to the power constraints of IoT devices,the well-performanced large models are not suitable for IoT malware *** this paper we propose a malware detection method based on Markov images and MobileNet,offering a cost-effective,efficient,and high-performing solution for malware ***,this paper innovatively analyzes the robustness of opcode sequences.

关键词： deep learning feature fusion malware detection opcode lightweight model

A Deep Learning-Based Crowd Counting Method and System Implementation on Neural Processing Unit Platform

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第4期75卷 493-512页

作者： Yuxuan Gu Meng Wu Qian Wang Siguang Chen Lijun Yang Nanjing University of Posts and Telecommunications NanjingP210023China

In this paper, a deep learning-based method is proposed for crowdcountingproblems. Specifically, by utilizing the convolution kernel densitymap, the ground truth is generated dynamically to enhance the featureextractingability of the generator model. Meanwhile, the “cross stage partial”module is integrated into congested scene recognition network (CSRNet) toobtain a lightweight network model. In addition, to compensate for the accuracydrop owing to the lightweight model, we take advantage of “structuredknowledge transfer” to train the model in an end-to-end manner. It aimsto accelerate the fitting speed and enhance the learning ability of the studentmodel. The crowd-counting system solution for edge computing is alsoproposed and implemented on an embedded device equipped with a neuralprocessing unit. Simulations demonstrate the performance improvement ofthe proposed solution in terms of model size, processing speed and *** performance on the Venice dataset shows that the mean absolute error(MAE) and the root mean squared error (RMSE) of our model drop by32.63% and 39.18% compared with CSRNet. Meanwhile, the performance onthe ShanghaiTech PartB dataset reveals that the MAE and the RMSE of ourmodel are close to those of CSRNet. Therefore, we provide a novel embeddedplatform system scheme for public safety pre-warning applications.

关键词： Crowd counting CSRNet dynamic density map lightweight model knowledge transfer

Two-Stage Edge-Side Fault Diagnosis Method Based on Double Knowledge Distillation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第9期76卷 3623-3651页

作者： Yang Yang Yuhan Long Yijing Lin Zhipeng Gao Lanlan Rui Peng Yu State Key Laboratory ofNetworking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing100876China School of Computer Science and Engineering Nanyang Technological University639798Singapore Science and Technology on Communication Networks Laboratory The 54th Research Institute of China Electronics Technology Group CorporationShijiazhuang050051China

With the rapid development of the Internet of Things(IoT),the automation of edge-side equipment has emerged as a significant *** existing fault diagnosismethods have the characteristics of heavy computing and storage load,and most of them have computational redundancy,which is not suitable for deployment on edge devices with limited resources and *** paper proposes a novel two-stage edge-side fault diagnosis method based on double knowledge ***,we offer a clustering-based self-knowledge distillation approach(Cluster KD),which takes the mean value of the sample diagnosis results,clusters them,and takes the clustering results as the terms of the loss *** utilizes the correlations between faults of the same type to improve the accuracy of the teacher model,especially for fault categories with high ***,the double knowledge distillation framework uses ordinary knowledge distillation to build a lightweightmodel for edge-side *** propose a two-stage edge-side fault diagnosismethod(TSM)that separates fault detection and fault diagnosis into different stages:in the first stage,a fault detection model based on a denoising auto-encoder(DAE)is adopted to achieve fast fault responses;in the second stage,a diverse convolutionmodel with variance weighting(DCMVW)is used to diagnose faults in detail,extracting features frommicro andmacro *** comparison experiments conducted on two fault datasets,it is proven that the proposed method has high accuracy,low delays,and small computation,which is suitable for intelligent edge-side fault *** addition,experiments show that our approach has a smooth training process and good balance.

关键词： Fault diagnosis knowledge distillation edge-side lightweight model high similarity

Tree Detection Algorithm Based on Embedded YOLO lightweight Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2024年第3期29卷 518-527页

作者：吕峰王新彦李磊江泉易政洋 School of Mechanical Engineering Jiangsu University of Science and TechnologyZhenjiang 212100JiangsuChina

To avoid colliding with trees during its operation,a lawn mower robot must detect the *** tree detection methods suffer from low detection accuracy(missed detection)and the lack of a lightweight *** this study,a dataset of trees was constructed on the basis of a real lawn *** to the theory of channel incremental depthwise convolution and residual suppression,the Embedded-A module is proposed,which expands the depth of the feature map twice to form a residual structure to improve the lightweight degree of the *** to residual fusion theory,the Embedded-B module is proposed,which improves the accuracy of feature-map downsampling by depthwise convolution and pooling *** Embedded YOLO object detection network is formed by stacking the embedded modules and the fusion of feature maps of different *** results on the testing set show that the Embedded YOLO tree detection algorithm has 84.17%and 69.91%average precision values respectively for trunk and spherical tree,and 77.04% mean average precision *** number of convolution parameters is 1.78×10^(6),and the calculation amount is 3.85 billion float operations per *** size of weight file is 7.11MB,and the detection speed can reach 179 frame/*** study provides a theoretical basis for the lightweight application of the object detection algorithm based on deep learning for lawn mower robots.

关键词： Embedded YOLO algorithm lightweight model machine vision tree detection mowing robot

Thermal Infrared Salient Human Detection model Combined with Thermal Features in Airport Terminal

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Transactions of Nanjing University of Aeronautics and Astronautics 2022年第4期39卷 434-449页

作者： YU Yuecheng LIU Chang WANG Chuan SHI Jinlong School of Computer Jiangsu University of Science and TechnologyZhenjiang 212100P.R.China

Target detection in low light background is one of the main tasks of night patrol robots for airport ***,if some algorithms can run on a robot platform with limited computing resources,it is difficult for these algorithms to ensure the detection accuracy of human body in the airport terminal. A novel thermal infrared salient human detection model combined with thermal features called TFSHD is proposed. The TFSHD model is still based on U-Net,but the decoder module structure and model lightweight have been redesigned. In order to improve the detection accuracy of the algorithm in complex scenes,a fusion module composed of thermal branch and saliency branch is added to the decoder of the TFSHD model. Furthermore,a predictive loss function that is more sensitive to high temperature regions of the image is designed. Additionally,for the sake of reducing the computing resource requirements of the algorithm,a model lightweight scheme that includes simplifying the encoder network structure and controlling the number of decoder channels is adopted. The experimental results on four data sets show that the proposed method can not only ensure high detection accuracy and robustness of the algorithm,but also meet the needs of real-time detection of patrol robots with detection speed above 40 f/s.

关键词： thermal infrared image human body detection saliency thermal features lightweight model