Aktuelle Publikationen

Dezember 2023

Guard-ring free InGaAs/InP single photon avalanche diodes for C-band quantum communication

Pascal Rustige, Patrick Runge, Martin Schell, Jan Krause, Lorenz Eckoldt

We present a guard-ring free InGaAs/InP single photon avalanche diode with 20 µm diameter for the optical C-band. At 225 K, 25.6 µs dead time and 17% detection efficiency, the dark count rate is 3 kcps with 0.5% afterpulsing probability. This...

November 2023

From Empirical Measurements to Augmented Data Rates: A Machine Learning Approach for MCS Adaptation in Sidelink Communication

Asif Abdullah Rokoni, Slawomir Stanczak, Martin Kasparick, Daniel Schäufele

Due to the lack of a feedback channel in the C-V2X sidelink, finding a suitable MCS level is a difficult task. In this paper, we propose an ML approach that uses quantile prediction to predict the MCS level with the highest achievable data rate....

November 2023

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations

Alexander Binder, Klaus-Robert Müller, Wojciech Samek, Grégoire Montavon, Sebastian Lapuschkin, Leander Weber

While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifically model randomization testing is often overestimated and regarded...

November 2023

Optimizing Explanations by Network Canonization and Hyperparameter Search

Frederick Pahde, Wojciech Samek, Alexander Binder, Sebastian Lapuschkin, Galip Ümit Yolcu

Rule-based and modified backpropagation XAI methods struggle with innovative layer building blocks and implementation-invariance issues. In this work we propose canonizations for popular deep neural network architectures and introduce an XAI...

November 2023

Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations

Maximilian Dreyer, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin, Reduan Achtibat

Applying traditional post-hoc attribution methods to segmentation or object detection predictors offers only limited insights, as the obtained feature attribution maps at input level typically resemble the models' predicted segmentation mask or...

November 2023

Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models

Frederick Pahde, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer

State-of-the-art machine learning models often learn spurious correlations embedded in the training data. This poses risks when deploying these models for high-stake decision-making, such as in medical applications like skin cancer detection. To...

November 2023

Channel estimation with Zadoff–Chu sequences in the presence of phase errors

Sven Wittig, Wilhelm Keusgen, Michael Peter

Due to their perfect periodic autocorrelation property, Zadoff–Chu sequences are often used as stimulus signals in the measurement of radio channel responses. In this letter, the cross-correlation of a linear shift-invariant system's response to...

November 2023

Langevin Cooling for Unsupervised Domain Translation

Vignesh Srinivasan, Klaus-Robert Müller, Wojciech Samek, Shinichi Nakajima

In this paper, we show that many of such unsuccessful samples in image-to-image translation lie at the fringe—relatively low-density areas of data distribution, where the DNN was not trained very well. To tackle this problem we propose to perform...

November 2023

Towards automated digital building model generation from floorplans and on-site images

Niklas Gard, Aleixo Cambeiro Barreiro

We propose a system to automatically generate enriched digital models from this data, consisting of two AI modules: one for 3D model reconstruction from 2D plans and one for 6D localization of images taken within a building in the corresponding...

November 2023

Characterization of C-Band Coherent Receiver Front-ends for Transmission Systems beyond S-C-L-Band

Robert Emmerich, Colja Schubert, Carsten Schmidt-Langhorst, Ronald Freund

Fraunhofer HHI Researchers investigate in this publication a cost-efficient capacity upgrade of optical transmission systems by the reuse of already deployed single mode fiber. This is enabled by the benefits of other transmission bands, to...

Oktober 2023

Pre-Training with Fractal Images Facilitates Learned Image Quality Estimation

Malte Silbernagel, Thomas Wiegand, Peter Eisert, Sebastian Bosse

Current image quality estimation relies on data-driven approaches, however the scarcity of annotated data poses a bottleneck. This paper introduces a novel pre-training approach utilizing synthetic fractal images. The proposed method is tested on...

Oktober 2023

A Differentiable Gaussian Prototype Layer for Explainable Fruit Segmentation

Michael Gerstenberger, Peter Eisert, Sebastian Bosse, Steffen Maaß

We introduce a GMM Layer for gradient-based prototype learning. It is used to cluster feature vectors by computing their probabilities for each gaussian and using the soft cluster assignment for prediction. Hence prototypical image regions can be...

Oktober 2023

Design and Fabrication of Crossing-free Waveguide Routing Networks using a Multi-layer Polymer-based Photonic Integration Platform

Madeleine Weigel, Martin Schell, Moritz Kleinert, Crispin Zawadzki, David de Felipe Mesquida, Martin Kresse, Norbert Keil, Hauke Conradi, Anja Scheu, Jakob Reck, Klara Mihov

A novel 16x4 crossing-free waveguide routing network on four layers of polymer-based stacked waveguides is presented. The design and fabricated device combine in-plane passive waveguide structures with vertical multimode interference couplers to...

September 2023

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation

Reduan Achtibat, Thomas Wiegand, Sebastian Bosse, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer, Ilona Eisenbraun

We introduce the Concept Relevance Propagation (CRP) approach, which combines the local and global perspectives and thus allows answering both the ‘where’ and ‘what’ questions for individual predictions. We demonstrate the capability of our...

September 2023

When it comes to Earth observations in AI for disaster risk reduction, is it feast or famine? A topical review

Monique Kuglitsch, Jackie Ma, Arif Albayrak, Allison Craddock, Andrea Toreti, Elena Xoplaki, Jürg Lüterbacher, Paula Padrino Vilela, Rui Kotani, Dominique Berod, Jon Cox

Given the number of in situ and remote (e.g. radiosonde/satellite) monitoring devices, there is a common perception that there are no limits to the availability of EO for immediate use in such AI-based models. However, a mere fraction of EO is...

September 2023

FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning

Felix Sattler, Wojciech Samek, Roman Rischke, Tim Korjakow

In this work, we propose FEDAUX, an extension to Federated Distillation, which, under the same set of assumptions, drastically improves the performance by deriving maximum utility from the unlabeled auxiliary data. Our proposed method achieves...

September 2023

Hybrid semantic clustering of 3D point clouds in construction

Marcus Zepp

In this work, we present an artificial intelligence (AI)-based semantic segmentation approach for three-dimensional (3D) point clouds which were generated from 2D images with a structure from motion (SfM) pipeline. We utilize state-of-the-art...

September 2023

3D Hyperspectral Light-Field Imaging: a first intraoperative implementation

Eric Wisotzky, Peter Eisert, Anna Hilsmann

Hyperspectral imaging is an emerging technology that has gained significant attention in the medical field due to its ability to provide precise and accurate imaging of biological tissues. The current methods of hyperspectral imaging, such as...

September 2023

Automatic Registration of Anatomical Structures of Stereo-Endoscopic Point Clouds

Sophie Beckmann, Peter Eisert, Anna Hilsmann, Jean-Claude Rosenthal, Eric Wisotzky

In this paper, we present an analysis and registration pipeline for confined point clouds acquired by stereo endoscopes into a fused representation. For a coarse registration, TEASER is applied, while a refinement is conducted utilizing...

September 2023

Unsupervised learning of style-aware facial animation from real acting performances

Wolfgang Paier, Peter Eisert, Anna Hilsmann

This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering. Training a VAE for geometry and texture yields a parametric model for...

Ergebnisse pro Seite10ǀ20ǀ30
Ergebnisse 1-20 von 241
<< < 1 2 3 4 5 6 7 8 > >>