Fluid Flow Mass Transport for Generative Networks
arXiv:1910.01694
Abstract
Generative Adversarial Networks have been shown to be powerful in generating content. To this end, they have been studied intensively in the last few years. Nonetheless, training these networks requires solving a saddle point problem that is difficult to solve and slowly converging. Motivated from techniques in the registration of point clouds and by the fluid flow formulation of mass transport, we investigate a new formulation that is based on strict minimization, without the need for the maximization. The formulation views the problem as a matching problem rather than an adversarial one and thus allows us to quickly converge and obtain meaningful metrics in the optimization path.
References in corpus (8)
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Point-Set Registration: Coherent Point Drift
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Improved Training of Wasserstein GANs
- Improved Techniques for Training GANs
- Towards Principled Methods for Training Generative Adversarial Networks
- Fast and Accurate Point Cloud Registration using Trees of Gaussian Mixtures
- An Efficient Algorithm for Matrix-Valued and Vector-Valued Optimal Mass Transport