Wasserstein-2 Generative Networks
arXiv:1909.13082
Abstract
We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance). The algorithm uses input convex neural networks and a cycle-consistency regularization to approximate Wasserstein-2 distance. In contrast to popular entropic and quadratic regularizers, cycle-consistency does not introduce bias and scales well to high dimensions. From the theoretical side, we estimate the properties of the generative mapping fitted by our algorithm. From the practical side, we evaluate our algorithm on a wide range of tasks: image-to-image color transfer, latent space optimal transport, image-to-image style transfer, and domain adaptation.
30 pages, 21 figures, 3 tables
References in corpus (14)
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Variational Inference with Normalizing Flows
- MMD GAN: Towards Deeper Understanding of Moment Matching Network
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- Stabilizing Training of Generative Adversarial Networks through Regularization
- Input Convex Neural Networks
- Amortised MAP Inference for Image Super-resolution
- Large-Scale Optimal Transport and Mapping Estimation
- Optimal transport mapping via input convex neural networks
- 2-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANs
- Stabilizing Adversarial Nets With Prediction Methods
- Regularity as Regularization: Smooth and Strongly Convex Brenier Potentials in Optimal Transport
Cited by in corpus (7)
- Optimal transport mapping via input convex neural networks
- Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
- On the Existence of Optimal Transport Gradient for Learning Generative Models
- Physics Informed Convex Artificial Neural Networks (PICANNs) for Optimal Transport based Density Estimation
- Input Convex Gradient Networks
- Understanding Entropic Regularization in GANs
- Approximating the Optimal Transport Plan via Particle-Evolving Method