Deconvolution Layer
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).
In case of stride two and padding, the transposed convolution would look like this (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.
