**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 $W$).

Dilated convolution with learnable spacings: a new method that improves the accuracy of state-of-the-art CNNs

DCLS

Dilated convolution with learnable spacings

Xavier Initialization

**Differentiable Augmentation (DiffAugment)** is a set of differentiable image transformations used to augment data during [GAN](https://paperswithcode.com/method/gan) training. The transformations are applied to the real and generated images. It enables the gradients to be propagated through the augmentation back to the generator, regularizes
the discriminator without manipulating the target distribution, and maintains the balance of training
dynamics. Three choices of transformation are preferred by the authors in their experiments: Translation, [CutOut](https://paperswithcode.com/method/cutout), and Color.

Year	2000
Data Source	CC BY-SA - https://paperswithcode.com