Temporal Convolutions
Gated Convolution
Introduced by Dauphin et al. in Language Modeling with Gated Convolutional NetworksA Gated Convolution is a type of temporal convolution with a gating mechanism. Zero-padding is used to ensure that future context can not be seen.
Source: Language Modeling with Gated Convolutional Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Inpainting | 6 | 6.82% |
| Object Detection | 4 | 4.55% |
| Denoising | 4 | 4.55% |
| Semantic Segmentation | 4 | 4.55% |
| Pose Estimation | 3 | 3.41% |
| Image Classification | 3 | 3.41% |
| Prediction | 3 | 3.41% |
| Mamba | 2 | 2.27% |
| Language Modeling | 2 | 2.27% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
1x1 Convolution
|
Convolutions | |
Convolution
|
Convolutions | |
GLU
|
Activation Functions |
