Involution: Inverting the Inherence of Convolution for Visual Recognition

Where convolutions have been the doing great at what it does, involution symmetrically inverts the inherent properties of convolutions. Where convs are spatial-agnostic and channel-specific operations, invs are spatial-specific and channel-agnostic operations.

My take on Involutions: GitHub - ariG23498/involution-tf: TensorFlow implementation of involution.

Here one can find the Involution Layer which has all the necessary code to build the kernel dynamically and also apply it on the input feature space. One can also pick the code up and apply the layer to any tf based architecture.

1 Like

Hey Folks,

I have also had the opportunity to write on this topics as a Keras example.

Link: Involutional neural networks

Any feedback is welcome. :slight_smile:

1 Like