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.
$$ f\left(x\right) = \max\left(0, x\right) $$
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 48 | 7.75% |
Image Segmentation | 34 | 5.49% |
Denoising | 25 | 4.04% |
Medical Image Segmentation | 21 | 3.39% |
Image Classification | 21 | 3.39% |
Classification | 19 | 3.07% |
Self-Supervised Learning | 17 | 2.75% |
Object Detection | 14 | 2.26% |
Image Generation | 12 | 1.94% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |