Augmented Sliced Wasserstein Distances In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. This repository provides the code to reproduce the experimental results in the paper augmented sliced wasserstein distances by xiongjie chen, yongxin yang and yunpeng li.
Augmented Sliced Wasserstein Distances Deepai In this section, we provide a brief review of concepts related to the proposed work, including the wasserstein distance, (generalized) radon transform and (generalized) sliced wasserstein distances. We introduce the augmented sliced wasserstein distance (aswd), developed by chen et al. (2021). the aswd first maps samples to a nonlinear surface by a neural network and linearly projects the mapped samples onto a one dimensional line, then measures the discrepancy of the distributions on the line. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces.
Augmented Sliced Wasserstein Distances Deepai In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks.
Generalized Sliced Wasserstein Distances Deepai In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks. In this work, we propose a new family of distance metrics, called augmented sliced wasserstein distances (aswds), constructed by first mapping samples to higher dimensional hypersurfaces parameterized by neural networks.
Comments are closed.