activity
20192021
most citedMissing Features Reconstruction Using a Wasserstein Generative Adversarial Imputation Network

10 citations · 31 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG20213 cited

Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks

Alexander Kovalenko, Pavel Kordík, Magda Friedjungová

Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks, where now excessively large models are…

cs.CV202110 cited

Image Inpainting Using Wasserstein Generative Adversarial Imputation Network

Daniel Vašata, Tomáš Halama, Magda Friedjungová

Image inpainting is one of the important tasks in computer vision which focuses on the reconstruction of missing regions in an image. The aim of this paper is to introduce an image…

cs.LG202010 cited

Missing Features Reconstruction Using a Wasserstein Generative Adversarial Imputation Network

Magda Friedjungová, Daniel Vašata, Maksym Balatsko +1

Missing data is one of the most common preprocessing problems. In this paper, we experimentally research the use of generative and non-generative models for feature reconstruction.…

cs.LG2020

Unsupervised Latent Space Translation Network

Magda Friedjungová, Daniel Vašata, Tomáš Chobola +1

One task that is often discussed in a computer vision is the mapping of an image from one domain to a corresponding image in another domain known as image-to-image translation. Cur…

cs.HC20194 cited

Constructing a Data Visualization Recommender System

Petra Kubernátová, Magda Friedjungová, Max van Duijn

Choosing a suitable visualization for data is a difficult task. Current data visualization recommender systems exist to aid in choosing a visualization, yet suffer from issues such…

cs.LG20194 cited

Missing Features Reconstruction and Its Impact on Classification Accuracy

Magda Friedjungová, Daniel Vašata, Marcel Jiřina

In real-world applications, we can encounter situations when a well-trained model has to be used to predict from a damaged dataset. The damage caused by missing or corrupted values…