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 ConvolutionsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Machine Translation | 4 | 16.67% |
Translation | 4 | 16.67% |
Object Detection | 2 | 8.33% |
Bias Detection | 1 | 4.17% |
RGB Salient Object Detection | 1 | 4.17% |
Salient Object Detection | 1 | 4.17% |
Automatic Speech Recognition (ASR) | 1 | 4.17% |
Punctuation Restoration | 1 | 4.17% |
Speech Recognition | 1 | 4.17% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |