反褶积
卷积(计算机科学)
图层(电子)
计算机科学
像素
代表(政治)
空格(标点符号)
光学(聚焦)
算法
人工智能
光学
物理
化学
有机化学
政治
人工神经网络
政治学
法学
操作系统
作者
Wenzhe Shi,José Caballero,Lucas Theis,Ferenc Huszár,Andrew P. Aitken,Christian Ledig,Zehan Wang
出处
期刊:Cornell University - arXiv
日期:2016-01-01
被引量:106
标识
DOI:10.48550/arxiv.1609.07009
摘要
In this note, we want to focus on aspects related to two questions most people asked us at CVPR about the network we presented. Firstly, What is the relationship between our proposed layer and the deconvolution layer? And secondly, why are convolutions in low-resolution (LR) space a better choice? These are key questions we tried to answer in the paper, but we were not able to go into as much depth and clarity as we would have liked in the space allowance. To better answer these questions in this note, we first discuss the relationships between the deconvolution layer in the forms of the transposed convolution layer, the sub-pixel convolutional layer and our efficient sub-pixel convolutional layer. We will refer to our efficient sub-pixel convolutional layer as a convolutional layer in LR space to distinguish it from the common sub-pixel convolutional layer. We will then show that for a fixed computational budget and complexity, a network with convolutions exclusively in LR space has more representation power at the same speed than a network that first upsamples the input in high resolution space.
科研通智能强力驱动
Strongly Powered by AbleSci AI