Manifold Learning Benefits GANs

TL;DR

This paper enhances GANs by integrating manifold learning into the discriminator, improving the quality of generated data through non-linear manifold constraints and outperforming existing methods.

Contribution

It introduces a novel approach that incorporates locality-constrained manifold learning into GAN discriminators, with adaptive balancing for better feature representation.

Findings

Non-linear manifolds outperform linear ones.

The method significantly outperforms state-of-the-art baselines.

Manifold learning improves GAN training stability and quality.

Abstract

In this paper, we improve Generative Adversarial Networks by incorporating a manifold learning step into the discriminator. We consider locality-constrained linear and subspace-based manifolds, and locality-constrained non-linear manifolds. In our design, the manifold learning and coding steps are intertwined with layers of the discriminator, with the goal of attracting intermediate feature representations onto manifolds. We adaptively balance the discrepancy between feature representations and their manifold view, which is a trade-off between denoising on the manifold and refining the manifold. We find that locality-constrained non-linear manifolds outperform linear manifolds due to their non-uniform density and smoothness. We also substantially outperform state-of-the-art baselines.