Ambient Hidden Space of Generative Adversarial Networks

TL;DR

This paper extends ambient modules to the hidden space of GAN generators, providing theoretical conditions and demonstrating practical effectiveness on benchmark datasets.

Contribution

It introduces a novel approach to applying ambient modules within the hidden space of GANs, with theoretical analysis and empirical validation.

Findings

The ambient hidden space method is practical for GAN training.

Theoretical conditions for the uniqueness of the ambient hidden generator.

Successful application on benchmark datasets.

Abstract

Generative adversarial models are powerful tools to model structure in complex distributions for a variety of tasks. Current techniques for learning generative models require an access to samples which have high quality, and advanced generative models are applied to generate samples from noisy training data through ambient modules. However, the modules are only practical for the output space of the generator, and their application in the hidden space is not well studied. In this paper, we extend the ambient module to the hidden space of the generator, and provide the uniqueness condition and the corresponding strategy for the ambient hidden generator in the adversarial training process. We report the practicality of the proposed method on the benchmark dataset.