</> Code with Papers by Syntology

Methods › General › Normalization › Weight Demodulation

Weight Demodulation

182 papers tagged archive 2025-07-28

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

Weight Modulation is an alternative to adaptive instance normalization for use in generative adversarial networks, specifically it is introduced in StyleGAN2. The purpose of instance normalization is to remove the effect of s - the scales of the features maps - from the statistics of the convolution’s output feature maps. Weight modulation tries to achieve this goal more directly. Assuming that input activations are i.i.d. random variables with unit standard deviation. After modulation and convolution, the output activations have standard deviation of:

σⱼ = √(∑_(i,k)wᵢⱼₖ′²)

i.e., the outputs are scaled by the L₂ norm of the corresponding weights. The subsequent normalization aims to restore the outputs back to unit standard deviation. This can be achieved if we scale (“demodulate”) each output feature map j by 1/σⱼ . Alternatively, we can again bake this into the convolution weights:

w″ᵢⱼₖ = w′ᵢⱼₖ / √(∑_(i, k)w′ᵢⱼₖ² + ϵ)

where ϵ is a small constant to avoid numerical issues.

Source: Analyzing and Improving the Image Quality of StyleGANSee Code · NVlabs/stylegan2

Papers archive 2025-07-28

30 shown of 182, 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

20 shown of 140 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
Image Generation53
Attribute20
Generative Adversarial Network20
Disentanglement13
Face Generation13
Image Manipulation13
Diversity11
Data Augmentation10
Face Recognition10
Conditional Image Generation7
Translation7
Domain Adaptation6
Face Swapping6
Image-to-Image Translation5
Knowledge Distillation5
Transfer Learning5
Image Reconstruction4
Segmentation4
Semantic Segmentation4
Style Transfer4

Usage over time archive 2025-07-28

Papers per year tagged with Weight Demodulation: 2019 to 2025, peak 55 55 0 2019: 1 paper 2019 2020: 23 papers 2020 2021: 52 papers 2021 2022: 55 papers 2022 2023: 34 papers 2023 2024: 15 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (182 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