Viet-Anh on Software Logo

What is: Dynamic Convolution?

SourcePay Less Attention with Lightweight and Dynamic Convolutions
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

DynamicConv is a type of convolution for sequential modelling where it has kernels that vary over time as a learned function of the individual time steps. It builds upon LightConv and takes the same form but uses a time-step dependent kernel:

DynamicConv(X,i,c)=LightConv(X,f(X_i)_h,:,i,c)\text{DynamicConv}\left(X, i, c\right) = \text{LightConv}\left(X, f\left(X\_{i}\right)\_{h,:}, i, c\right)