Approximating continuous convolutions for deep network compression

We present ApproxConv, a novel method for compressing the layers of a convolutional neural network. Reframing conventional discrete convolution as continuous convolution of parametrised functions over space, we use functional approximations to capture the essential structures of CNN filters with few...

Volledige beschrijving

Bibliografische gegevens
Hoofdauteurs: Costain, TW, Prisacariu, VA
Formaat: Conference item
Taal:English
Gepubliceerd in: British Machine Vision Association 2022

Gelijkaardige items