Cramer-Wold AutoEncoder

2 code implementations • ICLR 2019 • Szymon Knop, Jacek Tabor, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski

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.

Sliced generative models

no code implementations • 29 Jan 2019 • Szymon Knop, Marcin Mazur, Jacek Tabor, Igor Podolak, Przemysław Spurek

In this paper we discuss a class of AutoEncoder based generative models based on one dimensional sliced approach.

One-element Batch Training by Moving Window

1 code implementation • 30 May 2019 • Przemysław Spurek, Szymon Knop, Jacek Tabor, Igor Podolak, Bartosz Wójcik

Several deep models, esp.

LocoGAN -- Locally Convolutional GAN

1 code implementation • 18 Feb 2020 • Łukasz Struski, Szymon Knop, Jacek Tabor, Wiktor Daniec, Przemysław Spurek

In the paper we construct a fully convolutional GAN model: LocoGAN, which latent space is given by noise-like images of possibly different resolutions.

Position

Generative models with kernel distance in data space

1 code implementation • 15 Sep 2020 • Szymon Knop, Marcin Mazur, Przemysław Spurek, Jacek Tabor, Igor Podolak

First, an autoencoder based architecture, using kernel measures, is built to model a manifold of data.

Target Layer Regularization for Continual Learning Using Cramer-Wold Generator

1 code implementation • 15 Nov 2021 • Marcin Mazur, Łukasz Pustelnik, Szymon Knop, Patryk Pagacz, Przemysław Spurek

We propose an effective regularization strategy (CW-TaLaR) for solving continual learning problems.

Continual Learning