Recent publications

November 2023

Design and Characterization of Dispersion-Tailored Silicon Strip Waveguide toward Wideband Wavelength Conversion

Hidenobu Muranaka, Tomoyuki Kato, Shun Okada, Tokuharu Kimura, Yu Tanaka, Tsuyoshi Yamamoto, Isaac Sackey, Gregor Ronniger, Robert Elschner, Carsten Schmidt-Langhorst, Takeshi Hoshida

One of cost-effective ways to increase the transmission capacity of current standard wavelength division multiplexing (WDM) transmission systems is to use a wavelength band other than the C-band to transmit in multi-band. We proposed the concept...


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...


October 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...



Items per page10ǀ20ǀ30
Results 21-30 of 263
<< < 1 2 3 4 5 6 7 8 > >>