Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space

by   Khoa D. Doan, et al.

For a given image generation problem, the intrinsic image manifold is often low dimensional. We use the intuition that it is much better to train the GAN generator by minimizing the distributional distance between real and generated images in a small dimensional feature space representing such a manifold than on the original pixel-space. We use the feature space of the GAN discriminator for such a representation. For distributional distance, we employ one of two choices: the Fréchet distance or direct optimal transport (OT); these respectively lead us to two new GAN methods: Fréchet-GAN and OT-GAN. The idea of employing Fréchet distance comes from the success of Fréchet Inception Distance as a solid evaluation metric in image generation. Fréchet-GAN is attractive in several ways. We propose an efficient, numerically stable approach to calculate the Fréchet distance and its gradient. The Fréchet distance estimation requires a significantly less computation time than OT; this allows Fréchet-GAN to use much larger mini-batch size in training than OT. More importantly, we conduct experiments on a number of benchmark datasets and show that Fréchet-GAN (in particular) and OT-GAN have significantly better image generation capabilities than the existing representative primal and dual GAN approaches based on the Wasserstein distance.


page 5

page 11

page 12

page 13

page 14


Improving GANs Using Optimal Transport

We present Optimal Transport GAN (OT-GAN), a variant of generative adver...

IF-GAN: A Novel Generator Architecture with Information Feedback

This paper presents an alternative generator architecture for image gene...

Feature Quantization Improves GAN Training

The instability in GAN training has been a long-standing problem despite...

Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flow

In this paper, we investigate the training process of generative network...

Geometric Enclosing Networks

Training model to generate data has increasingly attracted research atte...

AWGAN: Empowering High-Dimensional Discriminator Output for Generative Adversarial Networks

Empirically multidimensional discriminator (critic) output can be advant...

A Characteristic Function Approach to Deep Implicit Generative Modeling

In this paper, we formulate the problem of learning an Implicit Generati...

Please sign up or login with your details

Forgot password? Click here to reset