Methods › General › Normalization › Conditional Instance Normalization
Conditional Instance Normalization
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.
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.
-
Multi-defect microscopy image restoration under limited data conditions 31 Oct 2019 · 0 repositories · arXiv:1910.14207
-
Exploring the structure of a real-time, arbitrary neural artistic stylization network 18 May 2017 · 20 repositories · arXiv:1705.06830
-
A Learned Representation For Artistic Style 24 Oct 2016 · 11 repositories · arXiv:1610.07629
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.
| Task | Papers |
|---|---|
| Data Augmentation | 1 |
| Diversity | 1 |
| Generative Adversarial Network | 1 |
| Image Restoration | 1 |
| Style Transfer | 1 |
Usage over time archive 2025-07-28
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
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