AI engineering glossary · Computer vision
What is transposed convolution?
Transposed convolution (also called Deconvolution): A learned layer that increases spatial size, working roughly in reverse of a strided convolution. It is used in decoders and segmentation networks to turn small feature maps back into full-resolution outputs, though it can leave checkerboard artefacts.
Transposed convolution: an example
A stride-2 transposed convolution turns a 14 x 14 feature map into a 28 x 28 one.
Related terms
More Computer vision terms
Where you learn it
Transposed convolution is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.