Activation Functions
Sinusoidal Representation Network
Introduced by Sitzmann et al. in Implicit Neural Representations with Periodic Activation FunctionsSiren, or Sinusoidal Representation Network, is a periodic activation function for implicit neural representations. Specifically it uses the sine as a periodic activation function:
$$ \Phi\left(x\right) = \textbf{W}_{n}\left(\phi_{n-1} \circ \phi_{n-2} \circ \dots \circ \phi_{0} \right) $$
Source: Implicit Neural Representations with Periodic Activation Functions
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Neural Rendering | 2 | 25.00% |
| Normalising Flows | 1 | 12.50% |
| Color Manipulation | 1 | 12.50% |
| Image Enhancement | 1 | 12.50% |
| Photo Retouching | 1 | 12.50% |
| Tone Mapping | 1 | 12.50% |
| Image Inpainting | 1 | 12.50% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
