TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Activation Normalization

Activation Normalization

GeneralIntroduced 200061 papers
Source Paper

Description

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 Using This Method

MARBLE: Material Recomposition and Blending in CLIP-Space2025-06-05PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation2025-06-01Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal2025-02-15GLow -- A Novel, Flower-Based Simulated Gossip Learning Strategy2025-01-15Swarm Intelligence-Driven Client Selection for Federated Learning in Cybersecurity applications2024-11-28For Overall Nighttime Visibility: Integrate Irregular Glow Removal With Glow-Aware Enhancement2024-09-23Super Monotonic Alignment Search2024-09-12Adaptative Context Normalization: A Boost for Deep Learning in Image Processing2024-09-07ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding2024-06-02Towards Greener Nights: Exploring AI-Driven Solutions for Light Pollution Management2024-04-15Consumer Behavior under Benevolent Price Discrimination2024-04-04A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint2024-03-27NightHaze: Nighttime Image Dehazing via Self-Prior Learning2024-03-12Harnessing Density Ratios for Online Reinforcement Learning2024-01-18An attempt to generate new bridge types from latent space of generative flow2024-01-18NDELS: A Novel Approach for Nighttime Dehazing, Low-Light Enhancement, and Light Suppression2023-12-11Enhancing Ligand Pose Sampling for Molecular Docking2023-11-30From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement2023-07-31Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS2023-05-28Generative Steganographic Flow2023-05-10