1 code implementation • 25 Nov 2021 • Maxim Samarin, Vitali Nesterov, Mario Wieser, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth
We address these shortcomings with a novel approach to cycle consistency.
1 code implementation • NeurIPS 2020 • Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek, Volker Roth
Our approach is based on the deep information bottleneck in combination with a continuous mutual information regulariser.
no code implementations • 31 Dec 2019 • Aleksander Wieczorek, Volker Roth
The actual mutual information consists of the lower bound which is optimised in DVIB and cognate models in practice and of two terms measuring how much the former requirement $T-X-Y$ is violated.
no code implementations • 19 Nov 2018 • Adam Kortylewski, Mario Wieser, Andreas Morel-Forster, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth, Thomas Vetter
Computer vision tasks are difficult because of the large variability in the data that is induced by changes in light, background, partial occlusion as well as the varying pose, texture, and shape of objects.
no code implementations • 6 Jul 2018 • Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek, Volker Roth
Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding.
no code implementations • ICLR 2018 • Aleksander Wieczorek, Mario Wieser, Damian Murezzan, Volker Roth
Building on that, we show how this transformation translates to sparsity of the latent space in the new model.
no code implementations • CVPR 2019 • Adam Kortylewski, Aleksander Wieczorek, Mario Wieser, Clemens Blumer, Sonali Parbhoo, Andreas Morel-Forster, Volker Roth, Thomas Vetter
In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter.
no code implementations • 1 Nov 2016 • Aleksander Wieczorek, Volker Roth
We propose a new method of discovering causal relationships in temporal data based on the notion of causal compression.
no code implementations • 6 Oct 2015 • Dinu Kaufmann, Sonali Parbhoo, Aleksander Wieczorek, Sebastian Keller, David Adametz, Volker Roth
This paper considers a Bayesian view for estimating a sub-network in a Markov random field.