Recent publications

May 2022

Towards Auditable AI Systems: From Principles to Practice

Christian Berghoff, Thomas Wiegand, Wojciech Samek, Markus Wenzel, Jona Böddinghaus, Vasilios Danos, Gabrielle Davelaar, Thomas Doms, Heiko Ehrich, Alexandru Forrai, Radu Grosu, Ronan Hamon, Henrik Junklewitz, Matthias Neu, Simon Romanski, Dirk Schlesinger, Jan-Eve Stavesand, Sebastian Steinbach, Arndt von Twickel, Robert Walter, Johannes Weissenböck

Auditing AI systems is a complex endeavour since multiple aspects have to be considered along the AI lifecycle that require multi-disciplinary approaches. AI audit methods and tools are in many cases subject of research and not practically...


May 2022

Low-Loss Bragg-ReflectionWaveguides for On-Chip Time-Bin Entanglement

Hannah Thiel, Moritz Kleinert, Hauke Conradi, Lennart Jehle, Robert Chapman, Stefan Frick, Gregor Weihs, Marita Wagner, Bianca Nardi, Alexander Schlager, Holger Suchomel, Martin Kamp, Sven Hofling, Christian Schneider

We fabricate low-loss AlGaAs Bragg-reflection waveguides for the creation of C-band photon pairs via parametric down-conversion. These photon pairs are used in a hybrid on-chip time-bin entanglement scheme.


April 2022

xxAI - Beyond Explainable AI

Andreas Holzinger, Klaus-Robert Müller, Wojciech Samek, Randy Goebel, Ruth Fong, Taesup Moon

This book takes next steps towards a broader vision for explainable AI in moving beyond explaining classifiers, to include explaining other kinds of models (e.g., unsupervised and reinforcement learning models) via a diverse array of XAI...


April 2022

Explaining the Predictions of Unsupervised Learning Models

Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek, Jacob R. Kauffmann

In this chapter, we review our recently proposed "neuralization-propagation" (NEON) approach for bringing XAI to workhorses of unsupervised learning. NEON first converts the unsupervised model into a functionally equivalent neural network so...


April 2022

ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs

Daniel Becking, Karsten Müller, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer

In this chapter, we develop and describe a novel quantization paradigm for DNNs: Our method leverages concepts of explainable AI (XAI) and concepts of information theory: Instead of assigning weight values based on their distances to the...


April 2022

A Reference Model for Channel Sounder Performance Evaluation, Validation and Comparison

Sven Wittig, Wilhelm Keusgen, Michael Peter

In this paper, we propose a detailed generic reference plane model for performance evaluation and system validation of radio channel sounders. It allows to abstractly describe a broad variety of channel sounder implementations and architectures...


April 2022

Enhancing mmWave Devices with Custom Lenses

Konstantin Koslowski, Wilhelm Keusgen, Michael Peter, Felix Baum, Luca Bühler

The mmWave band offers high bandwidths, but drawbacks such as limited range and susceptibility to blockage remain a challenge. In this paper, we take off-the-shelf mmWave devices in the 60 GHz band and combine them with custom lenses. As a...



March 2022

A new concept for spatially resolved coherent detection with vertically illuminated photodetectors targeting ranging applications

Pascal Rustige, Patrick Runge, Martin Schell, Francisco M. Soares, Jan Krause

This paper proposes a novel approach for coherent detection with double-side vertically illuminated photodetectors. Signal and local oscillator are injected collinearly from opposite sides of the photodetector chip. The concept inherently...


March 2022

Coherent Detection With Double-Side Vertically Illuminated Photodiodes for Spatially Resolved Ranging Applications

Pascal Rustige, Patrick Runge, Martin Schell, Felix Ganzer

We theoretically investigate and demonstrate coherent detection with double-side vertically illuminated photodiodes by injecting signal and local oscillator collinearly from opposite sides of the photodetector chip. A first proof of concept for...


March 2022

Hybrid Polymer THz Receiver PIC with Waveguide Integrated Photoconductive Antenna: Concept and 1st Characterization Results

Tianwen Qian, Norbert Keil, Martin Schell, Moritz Kleinert, Crispin Zawadzki, David DeFelipe, Moritz Baier, Simon Nellen, Björn Globisch, Hauke Conradi, Milan Deumer, Y Durvasa Gupta, Madeleine Weigel, Jakob Reck, Klara Mihov, Ben Schuler, Martin Kresse

An all-photonic THz-receiver PIC comprising an on-chip frequency stabilization scheme and a novel InP-based photoconductive antenna is presented in this paper. Characterization of the key photonic building blocks shows the functionality of the...


February 2022

Characterization, Monitoring, and Mitigation of Standard C-Band Transceivers I/Q Imbalance in Multiband Systems

Gabriele Di Rosa, Colja Schubert, Ronald Freund, Johannes Fischer, Andre Richter, Robert Emmerich, Matheus Ribeiro Sena

To keep up with the rapid growth in global traffic, next-generation optical communication networks aim to vastly increase capacity by exploiting a larger optical transmission window covering the S-C-L-band. To reuse current commercially available...


February 2022

Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation

Alexandra Zimmer, Peter Eisert, Anna Hilsmann, Wieland Morgenstern

We present a solution for Accurate and temporally consistent modeling of human performances from video sequences. In detail, we derive parameters of a sequence of body models, representing shape and motion of a person, including jaw poses, facial...


February 2022

From Explanations to Segmentation: Using Explainable AI for Image Segmentation

Johannes Wolf Künzel, Peter Eisert, Anna Hilsmann, Clemens Peter Seibold

The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of training samples has to be manually labeled on pixel-precision. In...


February 2022

Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects

Niklas Gard, Peter Eisert, Anna Hilsmann

We present a multi-object 6D detection and tracking pipeline for potentially similar and non-textured objects. The combination of a convolutional neural network for object classification and rough pose estimation with a local pose refinement and...


February 2022

Overview of the Neural Network Compression and Representation (NNR) Standard

Heiner Kirchhoffer, Karsten Müller, Werner Bailer, Fabien Racape, Wojciech Samek, Shan Liu, Miska M. Hannuksela, Paul Haase, Hamed Rezazadegan-Tavakoli, Francesco Cricri, Emre Aksu, Wei Jiang, Wei Wang, Swayambhoo Jain, Shahab Hamidi-Rad

Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks. The NNR standard contains quantization and an arithmetic coding scheme as core encoding and decoding technologies, as...


January 2022

Automated Damage Inspection of Power Transmission Towers from UAV Images

Aleixo Cambeiro Barreiro, Peter Eisert, Anna Hilsmann, Clemens Peter Seibold

This paper adresses the problem of structural damage detection in transmission towers, addressing these two common challenges: (i) the lack of freely available training data and the difficulty to collect it; (ii) fuzzy boundaries of what...


January 2022

Continuous wave terahertz receivers with 4.5 THz bandwidth and 112 dB dynamic range

Milan Deumer, Martin Schell, Simon Nellen, Björn Globisch, Robert Kohlhaas, Lars Liebermeister, Steffen Breuer, Sebastian Lauck

We present photomixers made of InGaAs:Fe as broadband receivers in optoelectronic cw THz systems. The improved resistivity and carrier lifetime of InGaAs:Fe enable us to measure a bandwidth of 4.5 THz with a peak dynamic range of 112 dB. When...


January 2022

ML-assisted QoT estimation: a dataset collection and data visualization for dataset quality evaluation

Geronimo Bergk, Johannes Fischer, Mohammad Behnam Shariati, Pooyan Safari

We present a publicly available dataset collection to open the problem of data-driven QoT estimation to the ML community. The dataset collection allows comparing various solutions presented by different research groups. Furthermore, we propose...


January 2022

Explaining Machine Learning Models for Clinical Gait Analysis

Djordje Slijepcevic, Wojciech Samek, Sebastian Lapuschkin, Fabian Horst, Wolfgang I. Schöllhorn, Matthias Zeppelzauer, Anna-Maria Raberger, Christian Breiteneder, Brian Horsak, Andreas Kranzl

This article investigates the usefulness of Explainable Artificial Intelligence (XAI) methods to increase transparency in automated clinical gait classification based on time series. For this purpose, predictions of state-of-the-art...


January 2022

Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Models

Christopher J. Anders, Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, David Neumann, Leander Weber

Contemporary learning models for computer vision are typically trained on very large (benchmark) datasets with millions of samples. These may, however, contain biases, artifacts, or errors that have gone unnoticed and are exploitable by the...


December 2021

Terahertz Multilayer Thickness Measurements: Comparison of Optoelectronic Time and Frequency Domain Systems

Lars Liebermeister, Martin Schell, Simon Nellen, Björn Globisch, Robert Kohlhaas, Steffen Breuer, Milan Deumer, Sebastian Lauck

We compare a state-of-the-art terahertz (THz) time domain spectroscopy (TDS) system and a novel optoelectronic frequency domain spectroscopy (FDS) system with respect to their performance in layer thickness measurements on dielectric samples....


December 2021

Inverse kinematics for full-body self representation in VR-based cognitive rehabilitation

Larissa Wagnerberger, Sebastian Bosse, Detlef Runde, David Przewozny, Paul Chojecki, Mustafa Tevfik Lafci

Being self-represented through an avatar increases embodiment and the feeling of presence in virtual reality. Nevertheless, currently users in VR are typically represented only by their hands, as not enough tracking data is available for full...


December 2021

Accurate human body reconstruction for volumetric video

Decai Chen, Oliver Schreer, Peter Eisert, Ingo Feldmann, Markus Worchel

In this work, we enhance a professional end-to-end volumetric video production pipeline to achieve high-fidelity human body reconstruction using only passive cameras.We introduce and optimize deep learning based multi-view stereo networks for...


November 2021

Fiber-based Frequency Modulated LiDAR With MEMS Scanning Capability for Long-range Sensing in Automotive Applications

Sarah Cwalina, Volker Jungnickel, Patrick Runge, Ronald Freund, Christoph Kottke, Pascal Rustige, Thomas Knieling, Shansan Gu-Stoppel, Jörg Albers, Norman Laske, Frank Senger, Lianzhi Wen, Fabio Giovanneschi, Erdem Altuntac, Avinash Nittur Ramesh, Maria Antonia Gonzalez Huici, Andries Küter, Sangeeta Reddy

Safe operation of driver assistance systems remains a challenge, especially at higher speeds. It requires sensor technology that is capable of detecting surrounding conditions even at large distances. LiDAR technology is a cornerstone of this...


November 2021

Linearity Characteristics of Avalanche Photodiodes For InP Based PICs

Tobias Beckerwerth, Patrick Runge, Martin Schell, Felix Ganzer, Robert Behrends

We demonstrate InP based PICs with MMIs and waveguide integrated avalanche photodiodes (APD). We investigate these devices regarding their DC and RF linearity characteristics and find a high bandwidth beyond 20 GHz and a dynamic range of 30 dB...


November 2021

On the Link between Subjective Score Prediction and Disagreement of Video Quality Metrics

Lohic Fotio Tiotsop, Sebastian Bosse, Florence Agboma, Glenn van Wallendael, Ahmed Aldahdooh, Lucjan Janowski, Marcus Barkowsky, Enrico Masala

 

It is common to observe signi?cant disagreements amongst the quality predictions of these VQMs for the same video sequence. Herein, a measure for quantifying the disagreement between VQMs is proposed. We propose a disagreement measure that...


November 2021

Demonstration of latency-aware 5G network slicing on optical metro networks

Mohammad Behnam Shariati, Ronald Freund, Johannes Fischer, R. Nejabati, Jörg-Peter Elbers, Dimitra Simeonidou, R. Casellas, O. González de Dios, A. Autenrieth, Luis Velasco, Ralf-Peter Braun, Annika Dochhan, Bodo Lent, Marc Ruiz, J.J. Pedreno-Manresa, A. S. Muqaddas, J. E. Lopez de Vergara, S. López-Buedo, F.J. Moreno, P. Pavón, S. Patri, A. Giorgetti, A. Sgambelluri, F. Cugini, L. Luque Canto

The H2020 METRO-HAUL European project has architected a latency-aware, cost-effective, agile, and programmable optical metro network. This includes the design of semidisaggregated metro nodes with compute and storage capabilities, which interface...


November 2021

Secure Multi-Party Computation and Statistics Sharing for ML Model Training in Multi-domain Multi-vendor Networks

Pooyan Safari, Johanna Fischer, Mohammad Behnam Shariati, Geronimo Bergk

We propose a secure aggregation algorithm that allows proprietary-owned domains, hosting statistically different datasets, train and operate ML models in a Horizontally Federated Learning fashion. The obtained results show a compelling test...


November 2021

Vertical Federated Learning for Privacy-Preserving ML Model Development in Partially Disaggregated Networks

Nazila Hashemi, Johannes Fischer, Mohammad Behnam Shariati, Pooyan Safari

We present a novel framework that enables vendors and operators, with partial access to operational and monitoring features of a service, to collaboratively develop a ML-assisted solution without revealing any business-critical raw data to each...


Items per page10ǀ20ǀ30
Results 211-240 of 328
<< < 4 5 6 7 8 9 10 11 > >>