Normalization

Adaptive Instance Normalization

Introduced by Huang et al. in Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

Adaptive Instance Normalization is a normalization method that aligns the mean and variance of the content features with those of the style features.

Instance Normalization normalizes the input to a single style specified by the affine parameters. Adaptive Instance Normaliation is an extension. In AdaIN, we receive a content input $x$ and a style input $y$, and we simply align the channel-wise mean and variance of $x$ to match those of $y$. Unlike Batch Normalization, Instance Normalization or Conditional Instance Normalization, AdaIN has no learnable affine parameters. Instead, it adaptively computes the affine parameters from the style input:

$$ \textrm{AdaIN}(x, y)= \sigma(y)\left(\frac{x-\mu(x)}{\sigma(x)}\right)+\mu(y) $$

Source: Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Generation 52 14.02%
Disentanglement 26 7.01%
Image-to-Image Translation 20 5.39%
Style Transfer 20 5.39%
Image Manipulation 14 3.77%
Face Generation 12 3.23%
Face Recognition 12 3.23%
Domain Adaptation 9 2.43%
Super-Resolution 9 2.43%

Components


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

Categories