GAD: A Global Attraction Dataset and Attraction Classification Based on Residual Dense Convolutional Neural Networks

机译：GAD：基于残留密集卷积神经网络的全球吸引力数据集和吸引力分类

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Over the past years, the development of big data have received great attention, and data growth continues to increase. Deep learning technologies have shown good performance in many practical applications. In this work, we proposed a new deep learning model with low complexity to deal with global attraction classification problem. Due to limited datasets in outdoor scenes, firstly, we constructed a new large-scale global attraction dataset (GAD), containing more than 380k images for the world’s 250 famous attractions. Then we propose a new attraction classification method, where a residual dense module is integrated into a low-complexity convolutional neural network model. Our proposed method is demonstrated to show better performance than several state-of-the-art deep convolutional neural network models on our constructed GAD dataset.

机译：在过去几年中，大数据的发展受到了极大的关注，数据增长持续增加。深度学习技术在许多实际应用中表现出良好的表现。在这项工作中，我们提出了一种新的深度学习模式，具有较低的复杂性，以应对全球吸引力分类问题。由于户外场景中的数据集有限，首先，我们构建了一个新的大型全球景点数据集（GAD），为世界250名着名景点提供了超过380K的图像。然后，我们提出了一种新的景点分类方法，其中剩余密度模块集成到低复杂度卷积神经网络模型中。我们提出的方法被证明在我们构造的GAD数据集中的若干最先进的深卷积神经网络模型显示出更好的性能。

著录项

来源
《IEEE International Conference on Consumer Electronics》|2021年|1-6|共6页
会议地点
作者
Kuan-Hsien Liu; Yu-Chen Lai; Tsung-Jung Liu;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Deep learning; Image recognition; Databases; Conferences; Big Data; Complexity theory; Convolutional neural networks;

机译：深入学习;图像识别;数据库;会议;大数据;复杂性理论;卷积神经网络;

相似文献

外文文献
中文文献
专利

1. Hyperspectral remote sensing image classification based on dense residual three-dimensional convolutional neural network [J] . Suting Chen, Meng Jin, Jie Ding Multimedia Tools and Applications . 2021,第2期

机译：基于密集残余三维卷积神经网络的高光谱遥感图像分类
2. Random Noise Attenuation Based on Residual Convolutional Neural Network in Seismic Datasets [J] . Yang Liuqing, Chen Wei, Liu Wei, Quality Control, Transactions . 2020,第期

机译：基于地震数据集残留卷积神经网络的随机噪声衰减
3. Integration of residual network and convolutional neural network along with various activation functions and global pooling for time series classification [J] . Zou Xiaowu, Wang Zidong, Li Qi, Neurocomputing . 2019,第Nova20期

机译：残差网络和卷积神经网络以及各种激活函数和全局池的集成，用于时间序列分类
4. Residual Convolutional Neural Networks with Global and Local Pathways for Classification of Focal Liver Lesions [C] . Dong Liang, Lanfen Lin, Hongjie Hu, Pacific Rim international conference on artificial intelligence . 2018

机译：具有全局和局部途径的残差卷积神经网络用于局灶性肝病变的分类
5. Deep Convolutional Neural Networks for the Classification of the EMBER Malware Dataset [D] . Nallamothu, Anudeep 2018

机译：深度卷积神经网络用于EMBER恶意软件数据集的分类
6. Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network [O] . Seung Seog Han, Gyeong Hun Park, Woohyung Lim, -1

机译：深度神经网络在灰指甲诊断中显示出与皮肤科医生相当且通常优于皮肤病的性能：通过基于区域的卷积深度神经网络自动构建灰指甲数据集
7. Densely Feature Fusion Based on Convolutional Neural Networks for Motor Imagery EEG Classification [O] . Donglin Li, Jianhui Wang, Jiacan Xu, 2019

机译：基于卷积神经网络的电机图像EEG分类密集融合
8. Controlling basins of attraction in a neural network-based telemetry monitor [R] . Bell, Benjamin, Eilbert, James L. 1988

机译：在基于神经网络的遥测监视器中控制吸引盆

GAD: A Global Attraction Dataset and Attraction Classification Based on Residual Dense Convolutional Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅