Deconvolution Layer

• Remember Other Answer

Deconvolution layer is a very unfortunate name and should rather be called a transposed convolutional layer.

Visually, for a transposed convolution with stride one and no padding, we just pad the original input (blue entries) with zeroes (white entries) (Figure 1).

Figure 1

In case of stride two and padding, the transposed convolution would look like this (Figure 2):

Figure 2

All credits for the great visualisations go to

• Vincent Dumoulin, Francesco Visin - A guide to convolution arithmetic for deep learning

You can find more visualisations of convolutional arithmetics here.