264 citations · 714 across the 19 of their papers we have counts for
22 papers
Application-driven Validation of Posteriors in Inverse Problems
Tim J. Adler, Jan-Hinrich Nölke, Annika Reinke +8
Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist. In response, poste…
Training Invertible Neural Networks as Autoencoders
The-Gia Leo Nguyen, Lynton Ardizzone, Ullrich Köthe
Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks. In this work,…
Noise-Net: Determining physical properties of HII regions reflecting observational uncertainties
Da Eun Kang, Ralf S. Klessen, Victor F. Ksoll +3
Stellar feedback, the energetic interaction between young stars and their birthplace, plays an important role in the star formation history of the universe and the evolution of the…
Towards Multimodal Depth Estimation from Light Fields
Titus Leistner, Radek Mackowiak, Lynton Ardizzone +2
Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi…
Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare
Jana Fragemann, Lynton Ardizzone, Jan Egger +1
Deep neural networks are commonly used for medical purposes such as image generation, segmentation, or classification. Besides this, they are often criticized as black boxes as the…
Exoplanet Characterization using Conditional Invertible Neural Networks
Jonas Haldemann, Victor Ksoll, Daniel Walter +6
The characterization of an exoplanet's interior is an inverse problem, which requires statistical methods such as Bayesian inference in order to be solved. Current methods employ M…
Emission-line diagnostics of HII regions using conditional Invertible Neural Networks
Da Eun Kang, Eric W. Pellegrini, Lynton Ardizzone +4
Young massive stars play an important role in the evolution of the interstellar medium (ISM) and the self-regulation of star formation in giant molecular clouds (GMCs) by injecting…
Conditional Invertible Neural Networks for Diverse Image-to-Image Translation
Lynton Ardizzone, Jakob Kruse, Carsten Lüth +3
We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images. This…
Benchmarking Invertible Architectures on Inverse Problems
Jakob Kruse, Lynton Ardizzone, Carsten Rother +1
Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems. Following up on this, we investigate how ten inverti…
Representing Ambiguity in Registration Problems with Conditional Invertible Neural Networks
Darya Trofimova, Tim Adler, Lisa Kausch +5
Image registration is the basis for many applications in the fields of medical image computing and computer assisted interventions. One example is the registration of 2D X-ray imag…
Invertible Neural Networks for Uncertainty Quantification in Photoacoustic Imaging
Jan-Hinrich Nölke, Tim Adler, Janek Gröhl +5
Multispectral photoacoustic imaging (PAI) is an emerging imaging modality which enables the recovery of functional tissue parameters such as blood oxygenation. However, the underly…
Learning Robust Models Using The Principle of Independent Causal Mechanisms
Jens Müller, Robert Schmier, Lynton Ardizzone +2
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness i…
Generative Classifiers as a Basis for Trustworthy Image Classification
Radek Mackowiak, Lynton Ardizzone, Ullrich Köthe +1
With the maturing of deep learning systems, trustworthiness is becoming increasingly important for model assessment. We understand trustworthiness as the combination of explainabil…
Stellar Parameter Determination from Photometry using Invertible Neural Networks
Victor F. Ksoll, Lynton Ardizzone, Ralf Klessen +7
Photometric surveys with the Hubble Space Telescope (HST) allow us to study stellar populations with high resolution and deep coverage, with estimates of the physical parameters of…
Invertible Networks or Partons to Detector and Back Again
Marco Bellagente, Anja Butter, Gregor Kasieczka +5
For simulations where the forward and the inverse directions have a physics meaning, invertible neural networks are especially useful. A conditional INN can invert a detector simul…
BayesFlow: Learning complex stochastic models with invertible neural networks
Stefan T. Radev, Ulf K. Mertens, Andreas Voss +2
Estimating the parameters of mathematical models is a common problem in almost all branches of science. However, this problem can prove notably difficult when processes and model d…
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
Lynton Ardizzone, Radek Mackowiak, Carsten Rother +1
The Information Bottleneck (IB) objective uses information theory to formulate a task-performance versus robustness trade-off. It has been successfully applied in the standard disc…
Out of distribution detection for intra-operative functional imaging
Tim J. Adler, Leonardo Ayala, Lynton Ardizzone +6
Multispectral optical imaging is becoming a key tool in the operating room. Recent research has shown that machine learning algorithms can be used to convert pixel-wise reflectance…
Guided Image Generation with Conditional Invertible Neural Networks
Lynton Ardizzone, Carsten Lüth, Jakob Kruse +2
In this work, we address the task of natural image generation guided by a conditioning input. We introduce a new architecture called conditional invertible neural network (cINN). T…
Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
Tim J. Adler, Lynton Ardizzone, Anant Vemuri +8
Purpose: Optical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to addres…
Analyzing Inverse Problems with Invertible Neural Networks
Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert +6
In many tasks, in particular in natural science, the goal is to determine hidden system parameters from a set of measurements. Often, the forward process from parameter- to measure…
A versatile, high-power 460nm laser system for Rydberg excitation of ultracold potassium
Alda Arias, Stephan Helmrich, Christoph Schweiger +3
We present a versatile laser system which provides more than 1.5W of narrowband light, tunable in the range from 455-463 nm. It consists of a commercial Titanium-Sapphire laser whi…