Reversible GANs for Memory-efficient Image-to-Image Translation

Tycho F.A. van der Ouderaa Daniel E. Worrall

University of Amsterdam

In CVPR 2019

Paper | Code

Abstract

The Pix2pix and CycleGAN losses have vastly improved the qualitative and quantitative visual quality of results in image-to-image translation tasks. We extend this framework by exploring approximately invertible architectures in 2D and 3D which are well suited to these losses. These architectures are approximately invertible by design and thus partially satisfy cycle-consistency before training even begins. Furthermore, since invertible architectures have constant memory complexity in depth, these models can be built arbitrarily deep. We are able to demonstrate superior quantitative output on the Cityscapes and Maps datasets at near constant memory budget.

Paper

arXiv:1902.02729, 2019

Citation

Tycho F.A. van der Ouderaa, Daniel E. Worrall. "Reversible GANs for Memory-efficient Image-to-Image Translation", in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

@inproceedings{vanderOuderaa2019revgan,
  title={Reversible GANs for Memory-efficient Image-to-Image Translation},
  author={van der Ouderaa, Worrall, Daniel E},
  booktitle={CVPR 2019},
  year={2019}
}

Bibtex

Code

A PyTorch implementation has been made available in this Github repository.
For questions about the code, please create a ticket on the github project or contact Tycho van der Ouderaa.

Related Work

Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. "Image-to-Image Translation with Conditional Adversarial Networks", in CVPR 2017.
Jun-Yan Zhu*, Taesung Park*, Phillip Isola, and Alexei A. Efros. "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks" in ICCV 2017.
Aidan N. Gomez, Mengye Ren, Raquel Urtasun, Roger B. Grosse. "The Reversible Residual Network: Backpropagation Without Storing Activations", in NIPS 2017.
Tycho F.A. van der Ouderaa, Daniel E. Worrall, Bram van Ginneken. "Chest CT Super-resolution and Domain-adaptation using Memory-efficient 3D Reversible GANs", in MIDL 2019.

Acknowledgements

We grateful to the Diagnostic Image Analysis Group (DIAG) of the Radboud University Medical Center, and in particular Prof. Dr. Bram van Ginneken for his collaboration on this project. We also thank the Netherlands Organisation for Scientific Research (NWO) for supporting this research and providing computational resources.