Euclidean Norm Regularization

GeneralIntroduced 20009 papers
Source Paper

Description

Euclidean Norm Regularization is a regularization step used in generative adversarial networks, and is typically added to both the generator and discriminator losses:

R_z=w_r⋅∣∣Δz∣∣2_2R\_{z} = w\_{r} \cdot ||\Delta{z}||^{2}\_{2}

where the scalar weight w_rw\_{r} is a parameter.

Image: LOGAN

Papers Using This Method

Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN2022-11-16Edge-based fever screening system over private 5G2022-02-08Sinogram Denoise Based on Generative Adversarial Networks2021-08-09Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior2021-06-18Volumetric Quantitative Ablation Margins for Assessment of Ablation Completeness in Thermal Ablation of Liver Tumors2021-03-10LOGAN: Local Group Bias Detection by Clustering2020-10-06Allpass Feedback Delay Networks2020-07-14LOGAN: Latent Optimisation for Generative Adversarial Networks2019-12-02Deep Compressed Sensing2019-05-16