15 citations · 44 across the 9 of their papers we have counts for
14 papers
Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data
Thomas Germer, Jan Robine, Sebastian Konietzny +2
Computed tomography (CT) has become an essential part of modern science and medicine. A CT scanner consists of an X-ray source that is spun around an object of interest. On the opp…
A Survey on Self-Supervised Representation Learning
Tobias Uelwer, Jan Robine, Stefan Sylvius Wagner +5
Learning meaningful representations is at the heart of many tasks in the field of modern machine learning. Recently, a lot of methods were introduced that allow learning of image r…
Transformer-based World Models Are Happy With 100k Interactions
Jan Robine, Marc Höftmann, Tobias Uelwer +1
Deep neural networks have been successful in many reinforcement learning settings. However, compared to human learners they are overly data hungry. To build a sample-efficient worl…
Deblurring Photographs of Characters Using Deep Neural Networks
Thomas Germer, Tobias Uelwer, Stefan Harmeling
In this paper, we present our approach for the Helsinki Deblur Challenge (HDC2021). The task of this challenge is to deblur images of characters without knowing the point spread fu…
Optimizing Intermediate Representations of Generative Models for Phase Retrieval
Tobias Uelwer, Sebastian Konietzny, Stefan Harmeling
Phase retrieval is the problem of reconstructing images from magnitude-only measurements. In many real-world applications the problem is underdetermined. When training data is avai…
A Closer Look at Reference Learning for Fourier Phase Retrieval
Tobias Uelwer, Nick Rucks, Stefan Harmeling
Reconstructing images from their Fourier magnitude measurements is a problem that often arises in different research areas. This process is also referred to as phase retrieval. In…
Learning to Detect Adversarial Examples Based on Class Scores
Tobias Uelwer, Felix Michels, Oliver De Candido
Given the increasing threat of adversarial attacks on deep neural networks (DNNs), research on efficient detection methods is more important than ever. In this work, we take a clos…
Non-Iterative Phase Retrieval With Cascaded Neural Networks
Tobias Uelwer, Tobias Hoffmann, Stefan Harmeling
Fourier phase retrieval is the problem of reconstructing a signal given only the magnitude of its Fourier transformation. Optimization-based approaches, like the well-established G…
Learning to Plan via a Multi-Step Policy Regression Method
Stefan Wagner, Michael Janschek, Tobias Uelwer +1
We propose a new approach to increase inference performance in environments that require a specific sequence of actions in order to be solved. This is for example the case for maze…
Smaller World Models for Reinforcement Learning
Jan Robine, Tobias Uelwer, Stefan Harmeling
Sample efficiency remains a fundamental issue of reinforcement learning. Model-based algorithms try to make better use of data by simulating the environment with a model. We propos…
Fast Multi-Level Foreground Estimation
Thomas Germer, Tobias Uelwer, Stefan Conrad +1
Alpha matting aims to estimate the translucency of an object in a given image. The resulting alpha matte describes pixel-wise to what amount foreground and background colors contri…
PyMatting: A Python Library for Alpha Matting
Thomas Germer, Tobias Uelwer, Stefan Conrad +1
An important step of many image editing tasks is to extract specific objects from an image in order to place them in a scene of a movie or compose them onto another background. Alp…
Phase Retrieval Using Conditional Generative Adversarial Networks
Tobias Uelwer, Alexander Oberstraß, Stefan Harmeling
In this paper, we propose the application of conditional generative adversarial networks to solve various phase retrieval problems. We show that including knowledge of the measurem…
On the Vulnerability of Capsule Networks to Adversarial Attacks
Felix Michels, Tobias Uelwer, Eric Upschulte +1
This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks. Recent work suggests that these architectures are more robust towards adver…