[sheerun]

When it comes to translation/rotation invariance, this is similar idea to "Harmonic Networks: Deep Translation and Rotation Equivariance" paper:

- https://arxiv.org/pdf/1612.04642.pdf

- https://www.youtube.com/watch?v=qoWAFBYOtoU

Maybe they can be combined?

[icc97]

Interesting links. That paper indicates that it's primary benefit is with rotations rather than translations. Regular CNNs are perfectly capable of dealing with translations.