Temporal Convolutions

Dynamic Convolution

Introduced by Wu et al. in Pay Less Attention with Lightweight and Dynamic Convolutions

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:

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

Source: Pay Less Attention with Lightweight and Dynamic Convolutions

Papers


Paper Code Results Date Stars

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories