3 citations · 6 across the 9 of their papers we have counts for
10 papers
Deep Multivariate Models with Parametric Conditionals
Dmitrij Schlesinger, Boris Flach, Alexander Shekhovtsov
We consider deep multivariate models for heterogeneous collections of random variables. In the context of computer vision, such collections may e.g. consist of images, segmentation…
Game-theoretic distributed learning of generative models for heterogeneous data collections
Dmitrij Schlesinger, Boris Flach
One of the main challenges in distributed learning arises from the difficulty of handling heterogeneous local models and data. In light of the recent success of generative models,…
Symmetric Equilibrium Learning of VAEs
Boris Flach, Dmitrij Schlesinger, Alexander Shekhovtsov
We view variational autoencoders (VAE) as decoder-encoder pairs, which map distributions in the data space to distributions in the latent space and vice versa. The standard learnin…
Enhancing Fairness of Visual Attribute Predictors
Tobias Hänel, Nishant Kumar, Dmitrij Schlesinger +4
The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We…
VAE Approximation Error: ELBO and Exponential Families
Alexander Shekhovtsov, Dmitrij Schlesinger, Boris Flach
The importance of Variational Autoencoders reaches far beyond standalone generative models -- the approach is also used for learning latent representations and can be generalized t…
A Connection between Feed-Forward Neural Networks and Probabilistic Graphical Models
Dmitrij Schlesinger
Two of the most popular modelling paradigms in computer vision are feed-forward neural networks (FFNs) and probabilistic graphical models (GMs). Various connections between the two…