[论文解读] Is the deconvolution layer the same as a convolutional layer?

Wenzhe Shi, José Caballero+5 more|arXiv (Cornell University)|Sep 22, 2016

Advanced Image Processing Techniques参考文献 4被引用 106

一句话总结

该注记澄清去卷积（转置和子像素）层之间的关系，并引入高效的 LR-space 卷积，认为在固定预算下 LR-space 卷积可以超过高分辨率上采样。

ABSTRACT

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.

研究动机与目标

• 解释去卷积层如何与标准卷积相关。
• 区分转置卷积、子像素卷积和高效的 LR-space（低分辨率空间）卷积。
• 展示在固定计算预算下，低分辨率空间中的卷积为何更有效。

提出的方法

• 讨论去卷积形式之间的关系（转置卷积、子像素卷积、高效子像素卷积）。
• 将它们的高效 LR-space 卷积作为与常见的子像素层不同的独特类型进行介绍。
• 在固定计算预算和复杂度下提供理论和概念比较。

实验结果

研究问题

• RQ1 所提出的层与去卷积层之间的关系是什么？
• RQ2 在固定预算下，低分辨率空间中的卷积为何更优？
• RQ3 转置卷积、子像素卷积和高效子像素卷积在表示能力和速度上有何差异？

主要发现

• 该注记澄清了去卷积变体之间的关系以及作者的高效 LR-space 卷积。
• 它将高效子像素卷积层与标准的子像素层区分开。
• 在固定计算预算下，采用 LR-space 卷积的网络在相同速度下具有更强的表示能力，相较于先上采样到高分辨率的网络。
• 该讨论为在实际 CVPR 问题中关于层选择提供了更好的见解。