Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network

机译：学习深度卷积神经网络的内部密集但外部稀疏结构

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Recent years have witnessed two seemingly opposite developments of deep convolutional neural networks (CNNs). On the one hand, increasing the density of CNNs (e.g., by adding cross-layer connections) achieves better performance on basic computer vision tasks. On the other hand, creating sparsity structures (e.g., through pruning methods) achieves a more slim network structure. Inspired by modularity structures in the human brain, we bridge these two trends by proposing a new network structure with internally dense yet externally sparse connections. Experimental results demonstrate that our new structure could obtain competitive performance on benchmark tasks (CIFAR10, CIFAR100. and ImageNet) while keeping the network structure slim.

机译：近年来，深度卷积神经网络（CNN）出现了两个看似相反的发展。一方面，增加CNN的密度（例如，通过添加跨层连接）可在基本的计算机视觉任务上实现更好的性能。另一方面，创建稀疏结构（例如，通过修剪方法）实现了更苗条的网络结构。受人脑模块化结构的启发，我们通过提出一种具有内部密集但外部稀疏连接的新网络结构来桥接这两个趋势。实验结果表明，我们的新结构可以在基准任务（CIFAR10，CIFAR100和ImageNet）上获得竞争性能，同时保持网络结构的苗条。

著录项

来源
《International Conference on Artificial Neural Networks》|2019年|247-262|共16页
会议地点
作者
Yiqun Duan; Chen Feng;
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
Hierarchical CNN; Evolutionary algorithms; Neural network structure;

机译：分层CNN;进化算法;神经网络结构;

相似文献

外文文献
中文文献
专利

1. Deep convolution neural networks to differentiate between COVID-19 and other pulmonary abnormalities on chest radiographs: Evaluation using internal and external datasets [J] . Cho Yongwon, Hwang Sung Ho, Oh Yu-Whan, International journal of imaging systems and technology . 2021,第3期

机译：深度卷积神经网络区分Covid-19和胸部射线照片的其他肺异常：使用内部和外部数据集进行评估
2. Deep Convolutional Neural Networks With Transfer Learning for Rectum Toxicity Prediction in Combined Brachytherapy and External Beam Radiation Therapy for Cervical Cancer [J] . Zhen X., Chen J., Zhong Z., International Journal of Radiation Oncology, Biology, Physics . 2017,第2Suppla期

机译：宫颈癌联合大学生术后直肠毒性预测的深度卷积神经网络及外梁辐射治疗宫颈癌
3. Application of Deep Convolutional Neural Networks in Attention-Deficit/Hyperactivity Disorder Classification: Data Augmentation and Convolutional Neural Network Transfer Learning [J] . Zhu Li, Chang Weike Journal of Medical Imaging and Health Informatics . 2019,第8期

机译：深度卷积神经网络在注意力缺陷/多动障碍分类中的应用：数据增强与卷积神经网络转移学习
4. Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network [C] . Yiqun Duan, Chen Feng International Conference on Artificial Neural Networks . 2019

机译：学习内部密集但外部稀疏结构的深卷积神经网络
5. Internal and External Feature Engineering Applied to Deep Learning with Convolutional Neural Networks for Monocular Relative Pose Estimation in Visual Odometry and Self-Localization [D] . Parkins, Franz Payton. 2020

机译：内部和外部特征工程应用于卷积神经网络的深度学习，用于视觉测量和自定位中的单眼相对姿态估计
6. Hierarchical Sparse Coding of Objects in Deep Convolutional Neural Networks [O] . Xingyu Liu, Zonglei Zhen, Jia Liu 2020

机译：深度卷积神经网络中对象的分层稀疏编码
7. Rapid Auto IMRT Planning Using Cascade Dense Convolutional Neural Network (CDCNN): A Feasibility Study for Fluence Map Prediction Using Deep Learning on Prostate IMRT Patients [O] . C. Wang, X. Li, Y. Chang, 2019

机译：快速自动IMRT规划，使用级联密集卷积神经网络（CDCNN）：使用深层学习前列腺IMRT患者的流量地图预测的可行性研究

Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network

摘要

著录项

相似文献

相关主题

期刊订阅