Sliced generative models
This work addresses generative modeling for AI/ML applications, but it appears incremental as it builds on existing AutoEncoder and sliced methods with minor improvements.
The paper tackles the problem of generative modeling by introducing a class of AutoEncoder-based models that use a one-dimensional sliced approach to reduce sample discrimination, finding that methods based on classical distances between samples yield a slightly faster decrease in Fréchet Inception Distance (FID) compared to those based on normality tests.
In this paper we discuss a class of AutoEncoder based generative models based on one dimensional sliced approach. The idea is based on the reduction of the discrimination between samples to one-dimensional case. Our experiments show that methods can be divided into two groups. First consists of methods which are a modification of standard normality tests, while the second is based on classical distances between samples. It turns out that both groups are correct generative models, but the second one gives a slightly faster decrease rate of Fréchet Inception Distance (FID).