DeepAI
Log In Sign Up

A study of traits that affect learnability in GANs

11/27/2020
by   Niladri Shekhar Dutt, et al.
14

Generative Adversarial Networks GANs are algorithmic architectures that use two neural networks, pitting one against the opposite so as to come up with new, synthetic instances of data that can pass for real data. Training a GAN is a challenging problem which requires us to apply advanced techniques like hyperparameter tuning, architecture engineering etc. Many different losses, regularization and normalization schemes, network architectures have been proposed to solve this challenging problem for different types of datasets. It becomes necessary to understand the experimental observations and deduce a simple theory for it. In this paper, we perform empirical experiments using parameterized synthetic datasets to probe what traits affect learnability.

READ FULL TEXT
07/12/2018

The GAN Landscape: Losses, Architectures, Regularization, and Normalization

Generative Adversarial Networks (GANs) are a class of deep generative mo...
10/02/2018

On Self Modulation for Generative Adversarial Networks

Training Generative Adversarial Networks (GANs) is notoriously challengi...
02/28/2021

Training Generative Adversarial Networks in One Stage

Generative Adversarial Networks (GANs) have demonstrated unprecedented s...
06/10/2021

A Neural Tangent Kernel Perspective of GANs

Theoretical analyses for Generative Adversarial Networks (GANs) generall...
05/19/2020

Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies

Despite its short history, Generative Adversarial Network (GAN) has been...
08/01/2017

Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis

Generative Adversarial Neural Networks (GANs) are applied to the synthet...
12/07/2018

Color Constancy by GANs: An Experimental Survey

In this paper, we formulate the color constancy task as an image-to-imag...