Methods › General › Normalization › Activation Normalization

Activation Normalization

61 papers tagged archive 2025-07-28

Introduced by Diederik P. Kingma et al. in Glow: Generative Flow with Invertible 1x1 Convolutions

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

Activation Normalization is a type of normalization used for flow-based generative models; specifically it was introduced in the GLOW architecture. An ActNorm layer performs an affine transformation of the activations using a scale and bias parameter per channel, similar to batch normalization. These parameters are initialized such that the post-actnorm activations per-channel have zero mean and unit variance given an initial minibatch of data. This is a form of data dependent initilization. After initialization, the scale and bias are treated as regular trainable parameters that are independent of the data.

PaperSourceSee Code · openai/glow

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Activation Flow; Activation Prompt; Activation Oracles; Activation Oracles; Batch Normalization; Group Normalization; Activation Steering; activation steering.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 61 · with a code link: 27 · where Syntology ran a sample: 11 (7 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (11 of 61 tagged: 7 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 61 of 61, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 86 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 Generation7
Text to Speech6
text-to-speech6
Anomaly Detection3
Density Estimation3
Flare Removal3
Image Enhancement3
Out of Distribution (OOD) Detection3
Unsupervised Anomaly Detection3
Attribute2
BIG-bench Machine Learning2
Dimensionality Reduction2
Federated Learning2
Image Dehazing2
Low-Light Image Enhancement2
Out-of-Distribution Detection2
Text-To-Speech Synthesis2
Variational Inference2
Zero-Shot Learning2
Adversarial Robustness1

Usage over time archive 2025-07-28

Papers per year tagged with Activation Normalization: 2018 to 2025, peak 11 11 0 2018: 1 paper 2018 2019: 9 papers 2019 2020: 10 papers 2020 2021: 11 papers 2021 2022: 6 papers 2022 2023: 9 papers 2023 2024: 11 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (61 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