检索结果-内蒙古大学图书馆

Lightweight parameter de-redundancy demoiréing network with adaptive wavelet distillation

JOURNAL OF real-time image processing 2024年第1期21卷 6-6页

作者： Chen, Jiacong Mao, Qingyu Bao, Youneng Huang, Yingcong Meng, Fanyang Liang, Yongsheng Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Guangdong Peoples R China Shenzhen Technol Univ Coll Big Data & Internet Shenzhen 518118 Guangdong Peoples R China Harbin Inst Technol Shenzhen Sch Elect & Informat Engn Shenzhen 518055 Guangdong Peoples R China Res Ctr Networks & Commun Pengcheng Lab Shenzhen 518055 Guangdong Peoples R China

Recently, deep convolutional neural networks (CNNs) have achieved significant advancements in single image demoireing. However, most of the existing CNN-based demoireing methods require excessive memory usage and computational cost, which considerably limit to apply on mobile devices. Additionally, most CNN-based methods employ expensive approaches to generate similar feature maps, thereby resulting in redundant parameters within these networks. To alleviate these issues, we propose a lightweight parameter de-redundancy network (PDNet) for image demoireing. Specifically, we present an efficient ghost block (EGB) that utilizes dilated convolution and cost-efficient operation, which significantly reduces parameters and extracts representative features. Meanwhile, we design a multi-scale shuffle fusion mechanism (MSFM) with a low amount of parameters to integrate different scales of features, which mitigates the information loss issue. To enable the lightweight network for learning latent moire removal knowledge better, we adopt adaptive wavelet distillation to guide the network training. Experimental results validate the efficacy of our proposed method, achieving comparable or even superior results to the state-of-the-art method, while utilizing only 26.32% of parameters and 29.59% of Macs. The source code will be publicly available at https://***/ChenJiaCong-1005/PDNet.

关键词： image demoireing Lightweight Knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

EfficientCLIP-GAN: Enabling real-time Text-to-image Synthesis

EfficientCLIP-GAN: Enabling Real-time Text-to-Image Synthesi...

引用

Progressive Innovations in Intelligent Systems and Data Science (ICPIDS), International Conference on

作者： Vinay Hajare Piyush Ghadge Harshad Deshmukh Akash Gaikwad Department of Computer Engineering Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798331534691

ISBN: (纸本)9798331534707

Synthesis of text to images has become a powerful technology, but existing methods often suffer from high computational demands, slow generation times and limited control over the generated images. This paper introduces EfficientCLIP-GAN, a new model for deep learning that addresses these limitations. EfficientCLIP-GAN using Generative Adversarial Networks (GANs) to their full potential and the pre-trained CLIP model to achieve superior efficiency, enhanced controllability and unprecedented speed. The proposed architecture integrates CLIP into the GAN framework, enabling efficient prompt understanding, image-text matching, and more discriminative power. EfficientCLIP-GAN demonstrate superior efficiency, require substantially less training data and processing power than other approaches. Furthermore, it facilitates precise control over the images that are produced based on textual description, ensuring precise adherence to user prompts. Notably EfficientCLIP-GAN generates high-resolution images ~100 times faster than existing approaches, allowing for real-time CPU-based inference. This exceptional speed and efficiency make the model accessible for deployment on the low-power devices, democratizing access to production of images from text. Experimental results on the CUB dataset validate the model's effectiveness in creating a variety of realistic bird representations from written specifications. EfficientCLIP-GAN exhibits rapid training and convergence due to CLIP integrated generator and discriminator, In contrast to diffusion and autoregressive models, our approach thus needs 3% training data and 5% learnable parameters.

关键词： Training Technological innovation Computational modeling Text to image Training data Process control Production Generative adversarial networks real-time systems Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Computational tissue staining of non-linear multimodal imaging using supervised and unsupervised deep learning

引用

BIOMEDICAL OPTICS EXPRESS 2021年第4期12卷 2280-2298页

作者： Pradhan, Pranita Meyer, Tobias Vieth, Michael Stallmach, Andreas Waldner, Maximilian Schmitt, Michael Popp, Juergen Bocklitz, Thomas Friedrich Schiller Univ Inst Phys Chem Jena Germany Friedrich Schiller Univ Abbe Ctr Photon Jena Germany Leibniz Hlth Technol Jena Leibniz Inst Photon Technol Jena Germany Klinikum Bayreuth Inst Pathol Bayreuth Germany Jena Univ Hosp Dept Internal Med Gastroenterol Hepatol & Infect Jena Germany Friedrich Alexander Univ Erlangen Nuremberg Erlangen Grad Sch Adv Opt Technol SAOT D-91052 Erlangen Germany Friedrich Alexander Univ Erlangen Nuremberg Med Dept 1 Erlangen Germany

Hematoxylin and Eosin (H&E) staining is the ?gold-standard? method in histopathol-ogy. However, standard H&E staining of high-quality tissue sections requires long sample preparation times including sample embedding, which restricts its application for ?real-time? disease diagnosis. Due to this reason, a label-free alternative technique like non-linear multi -modal (NLM) imaging, which is the combination of three non-linear optical modalities including coherent anti-Stokes Raman scattering, two-photon excitation fluorescence and second-harmonic generation, is proposed in this work. To correlate the information of the NLM images with H&E images, this work proposes computational staining of NLM images using deep learning models in a supervised and an unsupervised approach. In the supervised and the unsupervised approach, conditional generative adversarial networks (CGANs) and cycle conditional generative adversarial networks (cycle CGANs) are used, respectively. Both CGAN and cycle CGAN models generate pseudo H&E images, which are quantitatively analyzed based on mean squared error, structure similarity index and color shading similarity index. The mean of the three metrics calculated for the computationally generated H&E images indicate significant performance. Thus, utilizing CGAN and cycle CGAN models for computational staining is beneficial for diagnostic applications without performing a laboratory-based staining procedure. To the author?s best knowledge, it is the first time that NLM images are computationally stained to H&E images using GANs in an unsupervised manner.

关键词： image processing image quality Imaging techniques Phase imaging Raman scattering Speckle noise

来源：评论

学校读者我要写书评

暂无评论

Dynamic decision-making for knowledge-enabled distributed resource configuration in cloud manufacturing considering stochastic order arrival

引用

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING 2024年 87卷

作者： Zhang, Yi Zhang, Zequn Lu, Yuqian Zhu, Haihua Tang, Dunbing Nanjing Univ Aeronaut & Astronaut Coll Mech & Elect Engn Nanjing 210000 Peoples R China Univ Auckland Dept Mech & Mechatron Engn Auckland 1142 New Zealand

The emergence of COVID-19 caused the stagnation of production activities and promoted the changing market demand. These uncertainties not only brought great challenges to the manufacturing approaches led by a single enterprise, but also threatened the stability of inherent supply chain. To maintain market competitiveness, an efficient distributed manufacturing resource allocation method is urgently needed by manufacturers. Cloud manufacturing (CMfg) is an advanced service-oriented manufacturing paradigm that breaks physical space constraints to integrate distributed resources across enterprises, and provides on-demand configuration of manufacturing services for personalized consumer needs in real-time. The focus of this paper is to achieve dynamic configuration of distributed resources in CMfg considering stochastic order arrival, while reducing overall completion time and improving resource utilization. First, a dynamic knowledge graph for distributed resources is constructed, and its definition and construction methods are introduced. Secondly, semantic matching between massive optional manufacturing resources and multiple types of subtasks is achieved through knowledge extraction, thereby obtaining a candidate set of manufacturing resources that meet basic requirements for each subtask. An artificial intelligence (AI) scheduler based on deep reinforcement learning is developed, and order urgency is incorporated into the design of state observation vectors. AI scheduler can generate optimal decision results based on environmental observations, select high-quality manufacturing service compositions over candidate sets, and ultimately achieve efficient distributed resources configuration. Finally, Dueling DQN-based training method is put forward to optimize AI scheduler, enabling adaptable decision-making performance in dynamic environment. In the experiment, a simulation environment with 18 different settings is designed that considers stochastic processing time, r

关键词： Cloud manufacturing Multi -task scheduling deep reinforcement learning Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Nutrient Food Prediction through deep learning

Nutrient Food Prediction through Deep Learning

引用

2021 Asian Conference on Innovation in Technology, ASIANCON 2021

作者： Banerjee, Saikat Mondal, Abhoy Chand University of Burdwan The Department of Computer Science West Bengal Golapbag India

ISBN: (纸本)9781728185835

The lifespan of a man can be sustained only with adequate nourishment. To lead a productive, healthy life, human needs nutritious food. In this pandemic COVID-19 situation humans need more nutritious food for combating infectious disease along with a strong immune system in our body. Nutritious foods recognition is one of the major tasks for a customer. In large stores plenty of agricultural products are stored, then there needs a classification for separating normal food and nutritious food. The real time decision will alert the consumer by predicting nutritious foods. By the use of deep learning, it may be possible to classify nutritious food along with their nutrient content and give the possible particular rating view image through the deep learning method. Enormous development in deep learning is possible due to the advancement of the Convolutional Neural Network (CNN) algorithms. CNN is a modern technique inspired by biological neurons mainly used for image processing and data analysis, producing encouraging results. The principal objective of our work is to detect and segregate normal food and nutritious food. This is accomplished using the combination of both nutrition and image Classification techniques. Hence, the proposed system achieved average overall accuracy is more than 91%. © 2021 IEEE.

关键词： Nutrients

来源：评论

学校读者我要写书评

暂无评论

Smart Agriculture with Enhanced Accuracy for Fruit Detection Using Conv2D

Smart Agriculture with Enhanced Accuracy for Fruit Detection...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Yashfa Kamran Mahnur Tauqeer Moiz Ahmad Syed Muhammad Hamza Tauqeer Department of Electrical Engineering National University of Science and Technology Islamabad Pakistan TUM School of Engineering and Design Technical University of Munich Munich Germany Department of Electronics Engineering University of Engineering and Technology Taxila Pakistan

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

With the rise of deep learning and Machine learning, immense breakthroughs in the area of agricultural automation have now become possible. Most importantly, it is the kind of fruit ripeness that may be the main issue as it touches both the retailing and farming sectors. In this paper, Convolutional Neural Network (CNN) approach and 2-Dimensional Convolution (Conv2D) model is applied as a main part of differentiating between ripe and unripe fruits because of their main distinguishing feature. The model is refined through the use of image processing techniques like resizing and normalization, which make its generalization ability more robust. Using the Adam optimizer and the binary cross entropy loss function, the model is tuned for the binary classification task which we deal with. The results of the model can be observed through fruit maturity classification with training accuracy 99 percent and validation accuracy reaches 84 percent, Area Under curve (AUC) equals 0.92.

关键词： Training deep learning Smart agriculture Accuracy Automation Neural networks Data models real-time systems Convolutional neural networks Sorting

来源：评论

学校读者我要写书评

暂无评论

An image-based transfer learning approach for using in situ processing data to predict laser powder bed fusion additively manufactured Ti-6Al-4V mechanical properties

arXiv

引用

arXiv 2024年

作者： Luo, Qixiang Shimanek, John D. Simpson, Timothy W. Beese, Allison M. Department of Materials Science and Engineering Pennsylvania State University University ParkPA16802 United States Department of Industrial and Manufacturing Engineering Pennsylvania State University University ParkPA16802 United States Department of Mechanical Engineering Pennsylvania State University University ParkPA16802 United States

The mitigation of material defects from additive manufacturing (AM) processes is critical to reliability in their fabricated parts and is enabled by modeling the complex relations between available build monitoring signals and final mechanical performance. To this end, the present study investigates a machine learning approach for predicting mechanical properties for Ti-6Al-4V fabricated through laser powder bed fusion (PBF-LB) AM using in situ photodiode processing signals. Samples were fabricated under different processing parameters, varying laser powers and scan speeds for the purpose of probing a wide range of microstructure and property variations. Photodiode data were collected during fabrication, later to be arranged in image format and extracted to information-dense vectors by the transferal of deep convolutional neural network (DCNN) structures and weights pre-trained on a large computer vision benchmark image database. The extracted features were then used to train and test a newly designed regression model for mechanical properties. Average cross-validation accuracies were found to be 98.7% (r2 value of 0.89) for the prediction of ultimate tensile strength, which ranged from 900 to 1150 MPa in the samples studied, and 93.1% (r2 value of 0.96) for the prediction of elongation to fracture, which ranged from 0 to 17%. Thus, with high accuracy and hardware accelerated inference speeds, we demonstrate that a transfer learning framework can be used to predict strength and ductility of metal AM components based on processing signals in PBF-LB, illustrating a potential route toward real-time closed-loop control and process optimization of PBF-LB in industrial applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

real-time Detection of Tea Chrysanthemums in Complex Outdoor Scenes 26

Real-Time Detection of Tea Chrysanthemums in Complex Outdoor...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Zang, Siyang Shu, Lei Han, Ru Zhang, Feiya Zhang, Zhijun Deng, Der-Jiunn College of Artificial Intelligence Nanjing Agricultural University Nanjing210031 China School of Environmental Science and Engineering Guangdong University of Petrochemical Technology Guangdong Provincial Key Laboratory for Green Agricultural Production and Intelligent Equipment Maoming525000 China School of Engineering University of Lincoln LincolnLN67TS United Kingdom National Changhua University of Education Department of Computer Science and Information Engineering Changhua50007 Taiwan

ISBN: (纸本)9798331521950

Picking robots have emerged as a pivotal focus in smart agriculture, with precise target position detection being a key element for realizing robotic picking. However, detecting tea chrysanthemums presents various challenges, including their dynamic appearance, complex environmental conditions, susceptibility to occlusion and lighting variations, and the requirement for real-time embedded systems. When applied to complex outdoor scenes for Tea chrysanthemum targets, existing detection models suffer from drawbacks such as missed detections, low accuracy, and slow processing speeds. To address these challenges, we introduce YOLO-VTC (You Only Look Once-Varieties of Tea Chrysanthemum), a lightweight deep-learning model optimized for the Jetson Xavier NX platform. Detection experiments were conducted on image data capturing eight varieties of tea chrysanthemums in complex outdoor scenes collected in 2023. Results demonstrate that YOLO-VTC achieves an average accuracy of 86.60% and a peak accuracy of 97.10%, surpassing other lightweight networks with remarkable performance. Notably, the model effectively maintains a compact size of 6.58MB and has been successfully deployed on edge device platforms. © 2025 IEEE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Textual emotion classification using MPNet and cascading broad learning

引用

NEURAL NETWORKS 2024年 179卷 106582页

作者： Cao, Lihong Zeng, Rong Peng, Sancheng Yang, Aimin Niu, Jianwei Yu, Shui Guangdong Univ Foreign Studies Lab Language Engn & Comp Guangzhou 510006 Peoples R China Guangdong Univ Foreign Studies Ctr Linguist & Appl Linguist Guangzhou 510006 Peoples R China China Elect Prod Reliabil & Environm Testing Res I Guangzhou 511300 Peoples R China Lingnan Normal Univ Sch Comp Sci & Intelligence Educ Zhanjiang 524048 Peoples R China Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China Univ Technol Sydney Sch Software Sydney NSW 2007 Australia

As one of the most important tasks of natural language processing, textual emotion classification (TEC) aims to recognize and detect all emotions contained in texts. However, most existing methods are implemented using deep learning approaches, which may suffer from long training time and low convergence. Motivated by these challenges, in this paper, we provide a new solution for TEC by using cascading broad learning (CBL) and sentence embedding using a masked and permuted pre-trained language model (MPNet), named CBLMP. Texts are input into MPNet to generate sentence embedding containing emotional semantic information. CBL is adopted to improve the ability of feature extraction in texts and to enhance model performance for general broad learning, by cascading feature nodes and cascading enhancement nodes, respectively. The L-curve model is adopted to ensure the balance between under-regularization and over-regularization for regularization parameter optimization. Extensive experiments have been carried out on datasets of SMP2020-EWECT and SemEval-2019 Task 3, and the results show that CBLMP outperforms the baseline methods in TEC.

关键词： Textual emotion classification MPNet Cascading broad learning Regularization parameter optimization L-curve

来源：评论

学校读者我要写书评

暂无评论

A deep learning Method for Near-real-time Cloud and Cloud Shadow Segmentation from Gaofen-1 images

引用

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2020年第1期2020卷 1-13页

作者： Khoshboresh-Masouleh, Mehdi Shah-Hosseini, Reza Univ Tehran Coll Engn Sch Surveying & Geospatial Engn Tehran Iran

In this study, an essential application of remote sensing using deep learning functionality is presented. Gaofen-1 satellite mission, developed by the China National Space Administration (CNSA) for the civilian high-definition Earth observation satellite program, provides near-real-time observations for geographical mapping, environment surveying, and climate change monitoring. Cloud and cloud shadow segmentation are a crucial element to enable automatic near-real-time processing of Gaofen-1 images, and therefore, their performances must be accurately validated. In this paper, a robust multiscale segmentation method based on deep learning is proposed to improve the efficiency and effectiveness of cloud and cloud shadow segmentation from Gaofen-1 images. The proposed method first implements feature map based on the spectral-spatial features from residual convolutional layers and the cloud/cloud shadow footprints extraction based on a novel loss function to generate the final footprints. The experimental results using Gaofen-1 images demonstrate the more reasonable accuracy and efficient computational cost achievement of the proposed method compared to the cloud and cloud shadow segmentation performance of two existing state-of-the-art methods.

关键词： Climate change

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：