Methods › General › Normalization › Conditional Instance Normalization

Conditional Instance Normalization

3 papers tagged archive 2025-07-28

Introduced by Vincent Dumoulin et al. in A Learned Representation For Artistic Style

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Conditional Instance Normalization is a normalization technique where all convolutional weights of a style transfer network are shared across many styles. The goal of the procedure is transform a layer’s activations x into a normalized activation z specific to painting style s. Building off instance normalization, we augment the γ and β parameters so that they’re N ×C matrices, where N is the number of styles being modeled and C is the number of output feature maps. Conditioning on a style is achieved as follows:

z = γₛ((x - μ)/σ) + βₛ

where μ and σ are x’s mean and standard deviation taken across spatial axes and γₛ and βₛ are obtained by selecting the row corresponding to s in the γ and β matrices. One added benefit of this approach is that one can stylize a single image into N painting styles with a single feed forward pass of the network with a batch size of N.

PaperSourceSee Code · kewellcjj/pytorch-multiple-style-transfer

Papers archive 2025-07-28

3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Data Augmentation1
Diversity1
Generative Adversarial Network1
Image Restoration1
Style Transfer1

Usage over time archive 2025-07-28

Papers per year tagged with Conditional Instance Normalization: 2016 to 2019, peak 1 1 0 2016: 1 paper 2016 2017: 1 paper 2017 2018: 0 papers 2018 2019: 1 paper 2019
Papers per year the archive tags with this method, by the paper's archive date (3 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Normalization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections