Tessellated Wasserstein Auto-Encoders
Kuo Gai, Shihua Zhang

TL;DR
Tessellated Wasserstein Auto-Encoders (TWAE) improve non-adversarial generative models by tessellating the latent space to enhance distribution approximation accuracy, achieving competitive results with adversarial models.
Contribution
The paper introduces TWAE, a novel non-adversarial framework using centroidal Voronoi tessellation to improve distribution approximation in auto-encoders.
Findings
TWAE reduces discrepancy estimation error with larger samples and regions.
TWAE enhances generative performance measured by FID scores.
TWAE is competitive with WAE-GAN in generative ability.
Abstract
Non-adversarial generative models such as variational auto-encoder (VAE), Wasserstein auto-encoders with maximum mean discrepancy (WAE-MMD), sliced-Wasserstein auto-encoder (SWAE) are relatively easy to train and have less mode collapse compared to Wasserstein auto-encoder with generative adversarial network (WAE-GAN). However, they are not very accurate in approximating the target distribution in the latent space because they don't have a discriminator to detect the minor difference between real and fake. To this end, we develop a novel non-adversarial framework called Tessellated Wasserstein Auto-encoders (TWAE) to tessellate the support of the target distribution into a given number of regions by the centroidal Voronoi tessellation (CVT) technique and design batches of data according to the tessellation instead of random shuffling for accurate computation of discrepancy.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Adversarial Robustness in Machine Learning · Advanced Image Processing Techniques
MethodsUSD Coin Customer Service Number +1-833-534-1729
