Initialization

# Xavier Initialization

Xavier Initialization, or Glorot Initialization, is an initialization scheme for neural networks. Biases are initialized be 0 and the weights $W_{ij}$ at each layer are initialized as:

$$W_{ij} \sim U\left[-\frac{1}{\sqrt{n}}, \frac{1}{\sqrt{n}}\right]$$

Where $U$ is a uniform distribution and $n$ is the size of the previous layer (number of columns in $W$).

#### Papers

Paper Code Results Date Stars

General Classification 15 12.30%
Object Detection 14 11.48%
Image Classification 14 11.48%
Semantic Segmentation 6 4.92%
Quantization 4 3.28%
Autonomous Driving 3 2.46%
Specificity 3 2.46%
Object Recognition 3 2.46%
Video Summarization 2 1.64%

#### Components

Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign