# What are “VGG54” and “VGG22” derived from the VGG19 CNN?

In the paper Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network by Christian Ledig et al., the distance between images (used in the loss function) is calculated from feature maps extracted from the VGG19 network. The two used in the article are (a bit confusingly) called VGG22 and VGG54.

What are these feature maps?

What do the designations "22" and "54" mean?

• 19 is the number of layers. Probably the rest mean the same? – Alex Dec 31 '17 at 17:21
• If it was only that simple... ;-) These are designations of mapping from the VGG19, not networks in their own right. – Lafayette Jan 1 '18 at 9:46
• I never read the paper. This is the first thing that comes to mind when i see the acronym. – Alex Jan 1 '18 at 15:05
• Your assumption is indeed reasonable, but they do say that it is not the case, only the VGG19 network is used. – Lafayette Jan 1 '18 at 15:46

Reading the article, it seems like they define VGG54 as the loss calculated from the euclidean distance between the $\phi_{5,4}$ feature maps derived from both the high and low resolution images using the VGG19 network. Where $\phi_{i,j}$ is defined as "the feature map obtained by the j-th convolution (after activation) and before the i-th max-pooling layer within the VGG19 network".
• Can you please elaborate on "the feature map obtained by the j-th convolution (after activation) and before the i-th max-pooling layer within the VGG19 network"? $\phi_{5,4}$ means $4^{th}$ layer before $5^{th}$ max-pooling layer right? But $4^{th}$ layer has so many filters (I think 512). So we would have 512 feature spaces. Which one to choose from this? Also what does "after activation" mean? – Nagabhushan S N Nov 20 '18 at 17:31