3
$\begingroup$

I came across this line while reading the original paper on Spatial Transformers by Deepmind in the last paragraph of Sec 3.1:

The localisation network function floc() can take any form, such as a fully-connected network or a convolutional network, but should include a final regression layer to produce the transformation parameters θ.

I understand what regression is, but what is meant by a regression layer?

$\endgroup$
0
$\begingroup$

Basically, it means that the "localization network" should output a set of real valued parameters (typically 6 numbers). The word "regression" doesn't bear any specific meaning.

Any network that relies on the original image as input (directly or indirectly) and outputs 6 numbers, would work. And its last layer would qualify as "regression layer" as long as it is not restricted in the real domain (not normalized, softmaxed, etc)

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.