Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

TL;DR

This paper introduces DiscoGAN, a generative adversarial network-based method that automatically discovers cross-domain relations from unpaired data, enabling style transfer while maintaining key attributes.

Contribution

The paper presents a novel approach to discover cross-domain relations without paired data using GANs, facilitating style transfer and attribute preservation.

Findings

Successfully transfers style between domains

Discovers relations without paired training data

Preserves key attributes during transfer

Abstract

While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cross-domain relations given unpaired data. We propose a method based on generative adversarial networks that learns to discover relations between different domains (DiscoGAN). Using the discovered relations, our proposed network successfully transfers style from one domain to another while preserving key attributes such as orientation and face identity. Source code for official implementation is publicly available https://github.com/SKTBrain/DiscoGAN