PIE: Pseudo-Invertible Encoder

Jan Jetze Beitler, Ivan Sosnovik, Arnold Smeulders

Abstract: We consider the problem of information compression from high dimensional data. Where many studies consider the problem of compression by non-invertible trans- formations, we emphasize the importance of invertible compression. We introduce new class of likelihood-based auto encoders 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 outperform WAE and VAE in sharpness of the generated images.

Keywords: Invertible Mappings, Bijectives, Dimensionality reduction, Autoencoder

TL;DR: New Class of Autoencoders with pseudo invertible architecture