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 | 57 | 8.17% |
| Image Segmentation | 33 | 4.73% |
| Image Generation | 32 | 4.58% |
| Decoder | 28 | 4.01% |
| Denoising | 24 | 3.44% |
| Image Classification | 21 | 3.01% |
| Medical Image Segmentation | 17 | 2.44% |
| Object Detection | 15 | 2.15% |
| Self-Supervised Learning | 14 | 2.01% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
