74 citations · 360 across the 51 of their papers we have counts for
10 papers · 1 filter
LFA applied to CNNs: Efficient Singular Value Decomposition of Convolutional Mappings by Local Fourier Analysis
Antonia van Betteray, Matthias Rottmann, Karsten Kahl
The singular values of convolutional mappings encode interesting spectral properties, which can be used, e.g., to improve generalization and robustness of convolutional neural netw…
Poly-MgNet: Polynomial Building Blocks in Multigrid-Inspired ResNets
Antonia van Betteray, Matthias Rottmann, Karsten Kahl
The structural analogies of ResNets and Multigrid (MG) methods such as common building blocks like convolutions and poolings where already pointed out by He et al.\ in 2016. Multig…
ResBuilder: Automated Learning of Depth with Residual Structures
Julian Burghoff, Matthias Rottmann, Jill von Conta +3
In this work, we develop a neural architecture search algorithm, termed Resbuilder, that develops ResNet architectures from scratch that achieve high accuracy at moderate computati…
What should AI see? Using the Public's Opinion to Determine the Perception of an AI
Robin Chan, Radin Dardashti, Meike Osinski +7
Deep neural networks (DNN) have made impressive progress in the interpretation of image data, so that it is conceivable and to some degree realistic to use them in safety critical…
Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?
Hanno Gottschalk, Matthias Rottmann, Maida Saltagic
While automated driving is often advertised with better-than-human driving performance, this work reviews that it is nearly impossible to provide direct statistical evidence on the…
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Sebastian Houben, Stephanie Abrecht, Maram Akila +38
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These s…
A Convenient Infinite Dimensional Framework for Generative Adversarial Learning
Hayk Asatryan, Hanno Gottschalk, Marieke Lippert +1
In recent years, generative adversarial networks (GANs) have demonstrated impressive experimental results while there are only a few works that foster statistical learning theory f…
Detection of Iterative Adversarial Attacks via Counter Attack
Matthias Rottmann, Kira Maag, Mathis Peyron +2
Deep neural networks (DNNs) have proven to be powerful tools for processing unstructured data. However for high-dimensional data, like images, they are inherently vulnerable to adv…
Classification Uncertainty of Deep Neural Networks Based on Gradient Information
Philipp Oberdiek, Matthias Rottmann, Hanno Gottschalk
We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information…
Deep Bayesian Active Semi-Supervised Learning
Matthias Rottmann, Karsten Kahl, Hanno Gottschalk
In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to…