Authors: Jiqing Wu,Zhiwu Huang,Dinesh Acharya,Wen Li,Janine Thoma,Danda Pani Paudel,Luc Van Gool
Where published:
CVPR 2019 6
ArXiv: 1904.05408
Document:
PDF
DOI
Artifact development version:
GitHub
Abstract URL: http://arxiv.org/abs/1904.05408v2
In generative modeling, the Wasserstein distance (WD) has emerged as a useful
metric to measure the discrepancy between generated and real data
distributions. Unfortunately, it is challenging to approximate the WD of
high-dimensional distributions. In contrast, the sliced Wasserstein distance
(SWD) factorizes high-dimensional distributions into their multiple
one-dimensional marginal distributions and is thus easier to approximate. In
this paper, we introduce novel approximations of the primal and dual SWD.
Instead of using a large number of random projections, as it is done by
conventional SWD approximation methods, we propose to approximate SWDs with a
small number of parameterized orthogonal projections in an end-to-end deep
learning fashion. As concrete applications of our SWD approximations, we design
two types of differentiable SWD blocks to equip modern generative
frameworks---Auto-Encoders (AE) and Generative Adversarial Networks (GAN). In
the experiments, we not only show the superiority of the proposed generative
models on standard image synthesis benchmarks, but also demonstrate the
state-of-the-art performance on challenging high resolution image and video
generation in an unsupervised manner.