Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
This addresses the challenge of costly data pairing for cross-domain tasks, offering a method for unsupervised relation discovery.
The paper tackles the problem of discovering cross-domain relations without paired data, proposing DiscoGAN, a generative adversarial network that successfully transfers style between domains while preserving key attributes like orientation and face identity.
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