122 citations
- Technical University of MunichDE25 papers
- Ludwig-Maximilians-Universität MünchenDE19 papers
- Technische Universität DresdenDE6 papers
- Bielefeld UniversityDE5 papers
- Blekinge Institute of TechnologySE5 papers
- FortissDE5 papers
- Goethe University FrankfurtDE5 papers
- Iscte – Instituto Universitário de LisboaPT4 papers
- LMU KlinikumDE4 papers
- OTH RegensburgDE4 papers
- Universität der Bundeswehr MünchenDE4 papers
- Friedrich-Alexander-Universität Erlangen-NürnbergDE3 papers
23 papers · 1 filter
Visual Evaluation of Generative Adversarial Networks for Time Series Data
Hiba Arnout, Johannes Kehrer, Johanna Bronner +1
A crucial factor to trust Machine Learning (ML) algorithm decisions is a good representation of its application field by the training dataset. This is particularly true when parts…
Real-Time 3D Model Tracking in Color and Depth on a Single CPU Core
Wadim Kehl, Federico Tombari, Slobodan Ilic +1
We present a novel method to track 3D models in color and depth data. To this end, we introduce approximations that accelerate the state-of-the-art in region-based tracking by an o…
Neural Network Memorization Dissection
Jindong Gu, Volker Tresp
Deep neural networks (DNNs) can easily fit a random labeling of the training data with zero training error. What is the difference between DNNs trained with random labels and the o…
Dielectric Modeling of Oil-paper Insulation Systems at High DC Voltage Stress Using a Charge-carrier-based Approach
Tobias Gabler, Karsten Backhaus, Steffen Großmann +1
It is state-of-the-art to describe the dielectric behavior of an insulation material by its permittivity and its specific electric conductivity in order to estimate the dielectric…
Push it to the Limit: Discover Edge-Cases in Image Data with Autoencoders
Ilja Manakov, Volker Tresp
In this paper, we focus on the problem of identifying semantic factors of variation in large image datasets. By training a convolutional Autoencoder on the image data, we create en…
Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation
Ilja Manakov, Markus Rohm, Christoph Kern +3
We cast the problem of image denoising as a domain translation problem between high and low noise domains. By modifying the cycleGAN model, we are able to learn a mapping between t…