Tensorflow implementation of Involution
https://t.co/UM0KCrDOXz

The main concept is to symmetrically switch the inherent properties of convolution namely spatial-agnosticism and channel-specificity.

In the notebook, one will find an involution `tf.keras.layers.Layer`. It can be picked up and used in other architectures too.

The paper: https://t.co/qdoDthqHxd
@ykilcher's video on Involution: https://t.co/4OvDP8lTkI

More from All

You May Also Like