PIE: Pseudo-Invertible Encoder
Machine Learning
2021-11-02 v1 Computer Vision and Pattern Recognition
Abstract
We consider the problem of information compression from high dimensional data. Where many studies consider the problem of compression by non-invertible transformations, we emphasize the importance of invertible compression. We introduce new class of likelihood-based autoencoders with pseudo bijective architecture, which we call Pseudo Invertible Encoders. We provide the theoretical explanation of their principles. We evaluate Gaussian Pseudo Invertible Encoder on MNIST, where our model outperforms WAE and VAE in sharpness of the generated images.
Cite
@article{arxiv.2111.00619,
title = {PIE: Pseudo-Invertible Encoder},
author = {Jan Jetze Beitler and Ivan Sosnovik and Arnold Smeulders},
journal= {arXiv preprint arXiv:2111.00619},
year = {2021}
}