检索结果-内蒙古大学图书馆

Automatic concrete crack segmentation model based on transformer

AUTOMATION IN CONSTRUCTION 2022年 139卷

作者： Wang, Wenjun Su, Chao Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing 210098 Peoples R China

Routine visual inspection of concrete structures is essential to maintain safe conditions. Therefore, studies of concrete crack segmentation using deep learning methods have been extensively conducted in recent years. However, insufficient performance remains a major challenge in diverse field-inspection scenarios. In this study, a novel SegCrack model for pixel-level crack segmentation is therefore proposed using a hierarchically structured Transformer encoder to output multiscale features and a top-down pathway with lateral connections to progressively up-sample and fuse features from the deepest layer of the encoder. Furthermore, an online hard example mining strategy was adopted to strengthen the detection of hard samples and improve the model performance. The effect of dataset size on the segmentation performance was then investigated. The results indicated that SegCrack achieved a precision, recall, F1 score, and mean intersection over union of 96.66%, 95.46%, 96.05%, and 92.63%, respectively, using the test set.

关键词： Concrete crack Pixel-wise segmentation Visual transformer Self-attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive residential electricity load decomposition via low-resource model transferring

引用

JOURNAL OF BUILDING ENGINEERING 2023年 73卷

作者： Lin, Lin Shi, Jiancheng Ma, Changwen Zuo, Shi Zhang, Jie Chen, Cheng Huang, Nantian Jilin Inst Chem Technol Coll Informat & Control Engn Jilin 132022 Peoples R China Shanghai Second Polytech Univ Sch Environm & Mat Engn Shanghai 201209 Peoples R China State Grid Jilin Elect Power Co Ltd Econ & Tech Res Inst Changchun 130022 Peoples R China Northeast Dianli Univ Sch Elect Engn Jilin 132012 Peoples R China

Non-intrusive load decomposition (NILD) technology has a broad application prospect because it can deeply excavate the internal electricity consumption data of customers and obtain electricity consumption information. A non-intrusive load decomposition method based on model transfer is proposed to address the problem of insufficient accumulation of historical electricity consumption data of some household customers. Firstly, Time2vec, an embedding layer with time vectors, is introduced as an encoder to convert the time series into a continuous vector space, which improves the computational efficiency of the model for power time series information. Then, by introducing the Channel-wise attention mechanism, favorable residential electricity load characteristics can be effectively obtained. The model transfer method is used to fine-tune the pretrained model based on complete data to overcome the problem of insufficient accumulation of historical electricity consumption data of some households. The experimental results show that the proposed method is a significant improvement over the existing state-of-the-art methods. The proposed method significantly improves the accuracy of load decomposition while reducing the model parameters. The model parameters are reduced by 62.4%, and the average absolute error is reduced by 13.8%-59.3%. Even with a small number of data training source domains, the proposed method is still able to accurately obtain the power consumption information of each appliance, proving that the proposed method overcomes the problem of insufficient accumulation of electricity consumption data of household users.

关键词： Residential electricity load Non-intrusive load decomposition encoder-decoder Channel-wise attention mechanism Model transferring network

来源：评论

学校读者我要写书评

暂无评论

Graph neural network-based visual relationship and multilevel attention for image captioning

引用

JOURNAL OF ELECTRONIC IMAGING 2022年第5期31卷 053022-053022页

作者： Sharma, Himanshu Srivastava, Swati GLA Univ Dept Comp Engn & Applicat Mathura Uttar Pradesh India

With the remarkable success of the image captioning tasks, visual attention methods have become a vital part of captioning models. However, most attention-based image captioning methods do not consider any relationship among regions, which play a significant role in better image understanding. We proposed an image captioning method based on local relation network using a multilevel attention approach with graph neural network. It not only fully explores the relationship between the object and the image regions but also generates significant and context-based features corresponding to every region in the image. The attention employed in our work enhances the image representation capability of our method by focusing on a given image region and its related image regions. Thus addressing the relevant contextual information, spatial locations, and deep visual features leads to improve caption generation. We verified the effectiveness of the proposed model by conducting extensive experiments on three benchmark datasets: Flickr30k, MSCOCO, and nocaps. The results show the superiority of the proposed method over the existing methods both in quantitative and qualitative manners. Detailed ablation studies are conducted to communicate how each part would contribute to the final performance. (c) 2022 SPIE and IS&T

关键词： graph neural network relation network semantic attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A novel method for cage whirl motion capture of high-precision bearing inspired by U-Net

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartA期117卷

作者： Niu, Xiaoliang Yang, Zhaohui Zhou, Ningning Li, Chonghe Northwestern Polytech Univ Sch Aeronaut Xian 710072 Peoples R China Northwestern Polytech Univ Shenzhen Res & Dev Inst Shenzhen 518057 Peoples R China Beijing Inst Control Engn Beijing Key Lab Long Life Technol Precise Rotat & Beijing 100094 Peoples R China Aviat Ind Dev Res Ctr China AVICADR Res Inst Management Engn Beijing Peoples R China

To solve the problem of cage whirl motion capture and evaluation, this paper developed an efficient non -contact measurement method based on semantic segmentation technology. An encoder-decoder network whose backbone is U-Net is constructed by introducing residual learning and attention mechanism for cage motion state segmentation. A random move augmentation strategy is used to simulate the random movement of cage mass center. The network is trained with 1368 high-speed cage rotational images using the augmentation strategy. Additionally, 150 images are validation set, and 5000 images under different operating conditions are test set. A trained network is applied to the cage whirl motion capture under different operating conditions by matching the suitable parameters during the training phase. The results show that our method effectively predicts the trend of cage whirl motion, with the predicted cage whirl orbit used for the accurate analysis of cage rotational stability.

关键词： High-precision bearing Semantic segmentation encoder-decoder Random move augmentation Cage whirl motion

来源：评论

学校读者我要写书评

暂无评论

TAN: A Transferable Adversarial Network for DNN-Based UAV SAR Automatic Target Recognition Models

引用

DRONES 2023年第3期7卷 205-205页

作者： Du, Meng Sun, Yuxin Sun, Bing Wu, Zilong Luo, Lan Bi, Daping Du, Mingyang Natl Univ Def Technol Coll Elect Engn Hefei 230037 Peoples R China Sci & Technol Electroopt Informat Secur Control La Tianjin 300308 Peoples R China China Satellite Maritime Tracking & Control Dept Jiangyin 214430 Peoples R China Lanzhou Univ Coll Commun Engn Lanzhou 730030 Peoples R China

Recently, the unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) has become a highly sought-after topic for its wide applications in target recognition, detection, and tracking. However, SAR automatic target recognition (ATR) models based on deep neural networks (DNN) are suffering from adversarial examples. Generally, non-cooperators rarely disclose any SAR-ATR model information, making adversarial attacks challenging. To tackle this issue, we propose a novel attack method called Transferable Adversarial Network (TAN). It can craft highly transferable adversarial examples in real time and attack SAR-ATR models without any prior knowledge, which is of great significance for real-world black-box attacks. The proposed method improves the transferability via a two-player game, in which we simultaneously train two encoder-decoder models: a generator that crafts malicious samples through a one-step forward mapping from original data, and an attenuator that weakens the effectiveness of malicious samples by capturing the most harmful deformations. Particularly, compared to traditional iterative methods, the encoder-decoder model can one-step map original samples to adversarial examples, thus enabling real-time attacks. Experimental results indicate that our approach achieves state-of-the-art transferability with acceptable adversarial perturbations and minimum time costs compared to existing attack methods, making real-time black-box attacks without any prior knowledge a reality.

关键词： unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) automatic target recognition (ATR) deep neural network (DNN) adversarial example transferability encoder-decoder real-time attack

来源：评论

学校读者我要写书评

暂无评论

Wall segmentation in 2D images using convolutional neural networks

引用

PEERJ COMPUTER SCIENCE 2023年 9卷 e1565页

作者： Bjekic, Mihailo Lazovic, Ana Venkatachalam, K. Bacanin, Nebojsa Zivkovic, Miodrag Kvascev, Goran Nikolic, Bosko Everseen Belgrade Serbia Daon Belgrade Serbia Univ Hradec Kralove Fac Sci Dept Appl Cybernet Hradec Kralove Czech Republic Singidunum Univ Dept Informat & Comp Belgrade Serbia Univ Belgrade Sch Elect Engn Belgrade Serbia

Wall segmentation is a special case of semantic segmentation, and the task is to classify each pixel into one of two classes: wall and no-wall. The segmentation model returns a mask showing where objects like windows and furniture are located, as well as walls. This article proposes the module's structure for semantic segmentation of walls in 2D images, which can effectively address the problem of wall segmentation. The proposed model achieved higher accuracy and faster execution than other solutions. An encoder-decoder architecture of the segmentation module was used. Dilated ResNet50/101 network was used as an encoder, representing ResNet50/101 network in which dilated convolutional layers replaced the last convolutional layers. The ADE20K dataset subset containing only interior images, was used for model training, while only its subset was used for model evaluation. Three different approaches to model training were analyzed in the research. On the validation dataset, the best approach based on the proposed structure with the ResNet101 network resulted in an average accuracy at the pixel level of 92.13% and an intersection over union (IoU) of 72.58%. Moreover, all proposed approaches can be applied to recognize other objects in the image to solve specific tasks.

关键词： Semantic segmentation Wall segmentation encoder-decoder ADE20K PSPNet

来源：评论

学校读者我要写书评

暂无评论

ARF-Net: An Adaptive Receptive Field Network for breast mass segmentation in whole mammograms and ultrasound images

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2022年第PartA期71卷 103178-103178页

作者： Xu, Chunbo Qi, Yunliang Wang, Yiming Lou, Meng Pi, Jiande Ma, Yide Lanzhou Univ Sch Informat Sci & Engn Lanzhou Gansu Peoples R China

UNet adopting an encoder-decoder structure has been used widely in medical image segmentation tasks for its outstanding performance. However, in our work, we find that UNet has the worse segmentation performance of small masses. The reason behind this is that the sizes of receptive fields are limited. In this work, to address this issue, we develop a novel end-to-end model, Adaptive Receptive Field Network (ARF-Net), for the precise breast mass segmentation in whole mammographic images and ultrasound images. ARF-Net composes of an encoder network and a corresponding decoder network, followed by a pixel-wise classifier. In ARF-Net, a Selective Receptive Filed Module (SRFM) is proposed to allocate the suitable sizes of receptive fields to the breast masses of different sizes. SRFM consists of a Multiple Receptive Field Module (MRFM) for generating multiple receptive fields of different sizes and a Multi-Scale Selection Module (MSSM) for selecting the suitable sizes of receptive fields based on the objects' size. The proposed ARF-Net achieves the dice index of 86.1%, 85.75%, and 88.12% on the two mammographic databases (INbreast and CBIS-DDSM) and one ultrasonic database (UDIAT), respectively. Moreover, extensive ablation experiments show that ARF-Net transcends several state-of-the-art segmentation networks, and the developed MSSM exceeds several counterparts.

关键词： Segmentation Mammogram Ultrasound image Deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

TPET: Two-stage Perceptual Enhancement Transformer Network for Low-light Image Enhancement

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2022年第0期116卷

作者： Cui, Hengshuai Li, Jinjiang Hua, Zhen Fan, Linwei Shandong Technol & Business Univ Future Intelligent Comp Coinnovat Ctr Shandong Coll & Univ Sch Comp Sci & Technol Yantai Peoples R China Shandong Univ Finance & Econ Sch Comp Sci & Technol Jinan Peoples R China

Low-light images captured under low light or backlight conditions can suffer from different types of degradation such as low visibility, strong noise and color distortion. In this paper, to solve the degradation problem of low -light images, we propose Two-stage Perceptual Enhancement Transformer Network(TPET) for Low-light Image Enhancement by combining the advantages of local spatial perception of convolutional neural network and global spatial perception of transformer. The method is generally divided into two stages: feature extraction stage and detail fusion stage. First, in the feature extraction stage, the encoder composed of transformers performs global feature extraction and expands the receptive field. Since the transformer lacks the ability to capture local features, we introduce a perceptual enhancement module (PEM) to improve the interaction of local and global feature information. Second, between the corresponding encoding and decoding blocks in each layer, a feature fusion block (FFB) is introduced to compensate the feature information at different scales to improve the reusability of features and enhance the stability of the network. In addition, between the two stages, the local information features are redistributed and the network supervision capability is improved by introducing a self-calibration module (SCM). In the detail fusion stage, in order to further preserve the details of textural features of the image, we designed a detail enhancement unit (DEU) for recovering high-resolution enhanced images. Through qualitative comparison and quantitative analysis, our method outperforms other low-light image enhancement methods in terms of subjective visual effects and objective metrics values.

关键词： Low-light Image Enhancement Transformer encoder-decoder Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Image captioning using transformer-based double attention network

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期125卷

作者： Parvin, Hashem Naghsh-Nilchi, Ahmad Reza Mohammadi, Hossein Mahvash Univ Isfahan Fac Comp Engn Dept Artificial Intelligence Esfahan Iran

Image captioning generates a human-like description for a query image, which has attracted considerable attention recently. The most broadly utilized model for image description is an encoder-decoder structure, where the encoder extracts the visual information of the image, and the decoder generates textual descriptions of the image. Transformers have significantly enhanced the performance of image description models. However, a single attention structure in transformers cannot consider more complex relationships between key and query vectors. Furthermore, attention weights are assigned to entire candidate vectors based on the assumption that entire vectors are related. In this paper, a new double-attention framework is presented, which improves the encoder-decoder structure to consider image captioning problems. Hence, a local generator module and a global generator module are designed to predict textual descriptions collaboratively. The proposed approach improves Self-Attention (SA) from two aspects to enhance the performance of image description. First, a Masked Self-Attention module is presented to attend on the most relevant information. Second, to evade a single shallow attention distribution and make deeper internal relations, a Hybrid Weight Distribution (HWD) module is proposed, that develops SA to use the relations between key and query vectors efficiently. Experiments over the Flickr30k and MS-COCO datasets prove that the proposed approach achieves desirable performance on different evaluation measures compared to the state-of-the-art frameworks.

关键词： Self-attention Transformer Image captioning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Image captioning in Hindi language using transformer networks

引用

COMPUTERS & ELECTRICAL ENGINEERING 2021年 92卷 107114-107114页

作者： Mishra, Santosh Kumar Dhir, Rijul Saha, Sriparna Bhattacharyya, Pushpak Singh, Amit Kumar Indian Inst Technol Patna Dept Comp Sci & Engn Patna Bihar India Natl Inst Technol Patna Dept Comp Sci & Engn Patna Bihar India

Neural encoder-decoder architectures have been used extensively for image captioning. Con-volutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) are popularly used in encoder and decoder models. Recurrent Neural Networks are popular architectures in natural language processing used for language modeling, but they are sequential in nature. The transformer model can solve this problem of sequential dependency by using an attention mechanism. Many works are available for image captioning in the English language, but models for generating Hindi captions are limited;hence, we have tried to fill this gap. We have created the Hindi dataset for image captioning by manually translating the popular MSCOCO dataset from English to Hindi. Experimental results show that our proposed model outperforms other models. The proposed model has attained the BLEU-1 score of 62.9, BLEU-2 score of 43.3, BLEU-3 score of 29.1, and BLEU4 score of 19.0.

关键词： Image captioning Transformer model Deep learning encoder-decoder Hindi language

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：