.png){kind=icon}
返回
A fully trainable network with RNN-based pooling
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2019.02.004.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Pooling is an important component in convolutional neural networks (CNNs) for aggregating features and reducing computational burden. Compared with other components such as convolutional layers and fully connected layers which are completely learned from data, the pooling component is still handcrafted such as max pooling and average pooling. This paper proposes a learnable pooling function using recurrent neural networks (RNN) so that the pooling can be fully adapted to data and other components of the network, leading to an improved performance. Such a network with learnable pooling function is referred to as a fully trainable network (FTN). Experimental results demonstrate that the proposed RNN based pooling can well approximate the existing pooling functions with just one neuron, thus making it appropriate to be used as pooling function in a network with its rich representation capability. Furthermore, experiments have shown that the proposed FTN can achieve better performance than the existing pooling methods under similar network architectures for image classification. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Pooling
Recurrent neural network
Convolutional neural network
Deep learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
ARCH: Adaptive recurrent-convolutional hybrid networks for long-term action recognition.png)
NEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏
分享收藏Object class segmentation of RGB-D video using recurrent convolutional neural networks基于循环卷积神经网络的rgb-d视频对象类分割NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏 没有更多内容
没有更多内容