Large Scale GAN Training for High Fidelity Natural Image Synthesis

by   Andrew Brock, et al.
Heriot-Watt University

Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick", allowing fine control over the trade-off between sample fidelity and variety by truncating the latent space. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128x128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.3 and Frechet Inception Distance (FID) of 9.6, improving over the previous best IS of 52.52 and FID of 18.65.


page 1

page 4

page 7

page 12

page 13

page 14

page 15

page 16


Efficient Video Generation on Complex Datasets

Generative models of natural images have progressed towards high fidelit...

High-Fidelity Image Generation With Fewer Labels

Deep generative models are becoming a cornerstone of modern machine lear...

Improving the Speed and Quality of GAN by Adversarial Training

Generative adversarial networks (GAN) have shown remarkable results in i...

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

Computer graphics has experienced a recent surge of data-centric approac...

Make a Face: Towards Arbitrary High Fidelity Face Manipulation

Recent studies have shown remarkable success in face manipulation task w...

Group Equivariant Generative Adversarial Networks

Generative adversarial networks are the state of the art for generative ...

CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis

A persistent challenge in conditional image synthesis has been to genera...

Code Repositories


Deep Learning Journal Club

view repo

Please sign up or login with your details

Forgot password? Click here to reset