Activation Functions
Rectified Linear Units
Rectified Linear Units, or ReLUs, are a type of activation function that are linear in the positive dimension, but zero in the negative dimension. The kink in the function is the source of the non-linearity. Linearity in the positive dimension has the attractive property that it prevents non-saturation of gradients (contrast with sigmoid activations), although for half of the real line its gradient is zero.
$$ f\left(x\right) = \max\left(0, x\right) $$
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 56 | 8.12% |
| Image Segmentation | 33 | 4.78% |
| Image Generation | 30 | 4.35% |
| Decoder | 25 | 3.62% |
| Denoising | 24 | 3.48% |
| Image Classification | 22 | 3.19% |
| Medical Image Segmentation | 16 | 2.32% |
| Self-Supervised Learning | 14 | 2.03% |
| Object Detection | 14 | 2.03% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
