Methods › General › Normalization › Activation Normalization
Activation Normalization
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.
Papers archive 2025-07-28
30 shown of 61, 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.
-
MARBLE: Material Recomposition and Blending in CLIP-Space 5 Jun 2025 · 0 repositories · arXiv:2506.05313
-
PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation 1 Jun 2025 · 1 repository · arXiv:2506.01091
-
Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal 15 Feb 2025 · 0 repositories · arXiv:2502.10714
-
GLow -- A Novel, Flower-Based Simulated Gossip Learning Strategy 15 Jan 2025 · 1 repository · arXiv:2501.10463
-
Swarm Intelligence-Driven Client Selection for Federated Learning in Cybersecurity applications 28 Nov 2024 · 0 repositories · arXiv:2411.18877
-
For Overall Nighttime Visibility: Integrate Irregular Glow Removal With Glow-Aware Enhancement 23 Sep 2024 · 1 repository
-
Super Monotonic Alignment Search 12 Sep 2024 · 1 repository · arXiv:2409.07704
-
Adaptative Context Normalization: A Boost for Deep Learning in Image Processing 7 Sep 2024 · 0 repositories · arXiv:2409.04759
-
ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding 2 Jun 2024 · 1 repository · arXiv:2406.00578Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
-
Towards Greener Nights: Exploring AI-Driven Solutions for Light Pollution Management 15 Apr 2024 · 0 repositories · arXiv:2404.09453
-
Consumer Behavior under Benevolent Price Discrimination 4 Apr 2024 · 0 repositories · arXiv:2404.03581
-
A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint 27 Mar 2024 · 1 repository · arXiv:2403.18548Syntology ran 18 of 24 samples · 6 unverified · 24 pointer-only (licence)
-
NightHaze: Nighttime Image Dehazing via Self-Prior Learning 12 Mar 2024 · 0 repositories · arXiv:2403.07408
-
An attempt to generate new bridge types from latent space of generative flow 18 Jan 2024 · 1 repository · arXiv:2401.10299
-
Harnessing Density Ratios for Online Reinforcement Learning 18 Jan 2024 · 0 repositories · arXiv:2401.09681
-
NDELS: A Novel Approach for Nighttime Dehazing, Low-Light Enhancement, and Light Suppression 11 Dec 2023 · 0 repositories · arXiv:2312.06850
-
Enhancing Ligand Pose Sampling for Molecular Docking 30 Nov 2023 · 1 repository · arXiv:2312.00191Syntology ran 1 of 3 samples · 2 unverified
-
From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement 31 Jul 2023 · 1 repository · arXiv:2307.16783
-
Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS 28 May 2023 · 1 repository · arXiv:2305.17724
-
Generative Steganographic Flow 10 May 2023 · 0 repositories · arXiv:2305.05838
-
Tensor Slicing and Optimization for Multicore NPUs 6 Apr 2023 · 0 repositories · arXiv:2304.03013
-
ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus 28 Feb 2023 · 0 repositories · arXiv:2303.00069
-
GLOW: Global Layout Aware Attacks on Object Detection 27 Feb 2023 · 0 repositories · arXiv:2302.14166
-
FInC Flow: Fast and Invertible k ×k Convolutions for Normalizing Flows 23 Jan 2023 · 0 repositories · arXiv:2301.09266
-
Local Differential Privacy Image Generation Using Flow-based Deep Generative Models 20 Dec 2022 · 0 repositories · arXiv:2212.10688
-
Domain Adaptation with Adversarial Training on Penultimate Activations 26 Aug 2022 · 1 repository · arXiv:2208.12853
-
Out-of-distribution Detection via Frequency-regularized Generative Models 18 Aug 2022 · 1 repository · arXiv:2208.09083Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
-
Implementation Of Tiny Machine Learning Models On Arduino 33 BLE For Gesture And Speech Recognition 23 Jul 2022 · 0 repositories · arXiv:2207.12866
-
GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion 4 Jul 2022 · 0 repositories · arXiv:2207.01454
-
Revisiting Over-Smoothness in Text to Speech 26 Feb 2022 · 0 repositories · arXiv:2202.13066
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.
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