Cramer-Wold AutoEncoder
Not on the map. Why?
Abstract (arXiv)
We propose a new generative model, Cramer-Wold Autoencoder (CWAE). Following WAE, we directly encourage normality of the latent space. Our paper uses also the recent idea from Sliced WAE (SWAE) model, which uses one-dimensional projections as a method of verifying closeness of two distributions. The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE. We show that the Cramer-Wold metric between Gaussian mixtures is given by a simple analytic formula, which results in the removal of sampling necessary to estimate the cost function in WAE and SWAE models. As a consequence, while drastically simplifying the optimization procedure, CWAE produces samples of a matching perceptual quality to other SOTA models.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 May 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 3; 2023: 5.
10 papers.
- 2023Generative Sliced MMD Flows with Riesz Kernelscited by 37
- 2022Points2NeRF: Generating Neural Radiance Fields from 3D point cloudcited by 11
- 2022Diversity in deep generative models and generative AIcited by 2
- 2023Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized GANs Arecited by 2
- 2021HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Populationcited by 1
- 2021Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAEcited by 1
- 2023Cramer Type Distances for Learning Gaussian Mixture Models by Gradient Descentcited by 1
- 2022Algorithms that get old : the case of generative deep neural networkscited by 0
- 2023Joint Distributional Learning via Cramer-Wold Distancecited by 0
- 2023Balanced Marginal and Joint Distributional Learning via Mixture Cramer-Wold Distancecited by 0
- 2023Balanced Marginal and Joint Distributional Learning via Mixture Cramer-Wold Distance6 Dec 2023
- 2023Joint Distributional Learning via Cramer-Wold Distance25 Oct 2023
- 2023Cramer Type Distances for Learning Gaussian Mixture Models by Gradient Descent13 Jul 2023
- 2023Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized GANs Are1 Jun 2023
- 2023Generative Sliced MMD Flows with Riesz Kernels19 May 2023
- 2022Points2NeRF: Generating Neural Radiance Fields from 3D point cloud2 Jun 2022
- 2022Diversity in deep generative models and generative AI19 Feb 2022
- 2022Algorithms that get old : the case of generative deep neural networks7 Feb 2022
- 2021Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE19 Oct 2021
- 2021HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population3 Aug 2021