On Noise Injection in Generative Adversarial Networks

06/10/2020
by   Ruili Feng, et al.
0

Noise injection has been proved to be one of the key technique advances in generating high-fidelity images. Despite its successful usage in GANs, the mechanism of its validity is still unclear. In this paper, we propose a geometric framework to theoretically analyze the role of noise injection in GANs. Based on Riemannian geometry, we successfully model the noise injection framework as fuzzy equivalence on the geodesic normal coordinates. Guided by our theories, we find that the existing method is incomplete and a new strategy for noise injection is devised. Experiments on image generation and GAN inversion demonstrate the superiority of our method.

READ FULL TEXT

page 7

page 8

page 14

research
11/06/2018

Student's t-Generative Adversarial Networks

Generative Adversarial Networks (GANs) have a great performance in image...
research
01/29/2019

Generative Adversarial Networks for geometric surfaces prediction in injection molding

Geometrical and appearance quality requirements set the limits of the cu...
research
12/05/2020

Optimal polymer slugs injection curves

In the paper we study miscible injection of liquids with decreasing visc...
research
05/14/2020

Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in GANs

In the generator of typical Generative Adversarial Networks (GANs), a no...
research
09/27/2018

Introducing Noise in Decentralized Training of Neural Networks

It has been shown that injecting noise into the neural network weights d...
research
06/05/2023

Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware

Existing methods to recover model accuracy on analog-digital hardware in...
research
10/24/2022

Noise Injection as a Probe of Deep Learning Dynamics

We propose a new method to probe the learning mechanism of Deep Neural N...

Please sign up or login with your details

Forgot password? Click here to reset