What are the recommended ways to change shape of feature maps channel wise other than using Convolutional neural networks?

Asked Oct 11 '21 at 23:08

Active Oct 11 '21 at 23:18

Viewed 39 times

Suppose I have a feature map with size $C_1 \times H \times W$. And I need to convert it into a feature map of size $C_2 \times H \times W$.

One way to do this is to use convolutional neural networks as Conv2d($C_1, C_2$)

I want to know whether there are any other ways in Literature to perform the desired operation?

edited Oct 11 '21 at 23:18

asked Oct 11 '21 at 23:08

hanugm

2

any specific goal in mind when thinking about resizing these feature maps? from the way the question is phrased now it seems you're asking for a generic list that potentially include any matrix operation – Edoardo Guerriero Oct 12 '21 at 07:54
1

@EdoardoGuerriero Goal is to down-sample only, but without learning parameters. – hanugm Oct 12 '21 at 08:47

0 Answers0