Recent publications

August 2021

Explain and Improve: LRP-Inference Fine Tuning for Image Captioning Models

Jiamei Sun, Wojciech Samek, Alexander Binder, Sebastian Lapuschkin

This paper analyzes the predictions of image captioning models with attention mechanisms beyond visualizing the attention itself. We compare the interpretability of attention heatmaps systematically against the explanations. We demonstrate that...


August 2021

Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints

Felix Sattler, Klaus-Robert Müller, Wojciech Samek

Federated learning (FL) is the most widely adopted framework for collaborative training of deep learning models under privacy constraints. Albeit its popularity, it has been observed that FL yields suboptimal results if the clients’ data...


August 2021

S-Band Transmission with Off-the-Shelf C-Band Components Enabled by Nonlinear Predistortion based on Coherent System Identification

Robert Emmerich, Colja Schubert, Carsten Schmidt-Langhorst, Ronald Freund, Robert Elschner, Isaac Sackey, Mustafa Sezer Erkilinc, Matheus Ribeiro Sena

Nonlinear Predistortion based on Coherent System Identification Text: In order to cope with the rapid traffic growth and as well reducing the cost-per-bit, reuse of the legacy optical fiber infrastructure is one of the main objectives for...


August 2021

FantastIC4: A Hardware-Software Co-Design Approach for Efficiently Running 4bit-Compact Multilayer Perceptrons

Simon Wiedemann, Thomas Wiegand, Wojciech Samek, Friedel Gerfers, Daniel Becking, Suhas Shivapakashy, Pablo Wiedemann

With the growing demand for deploying Deep Learning models to the “edge”, it is paramount to develop techniques that allow to execute models within very tight and limited resource constraints. In this work we propose a software-hardware...


August 2021

Zero on Shape: A Generic 2D-3D Instance Similarity Metric learned from Synthetic Data

Maciej Janik, Peter Eisert, Anna Hilsmann, Niklas Gard

We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape. Our system is optimised for Zero-Shot retrieval, meaning it can recognise shapes never shown in training


July 2021

All-Indoor Optical Customer Premises Equipment for Fixed Wireless Access

Dominic Schulz, Volker Jungnickel, Ronald Freund, Christoph Kottke, Peter Hellwig, Julian Hohmann, Ralf-Peter Braun, Frank Geilhardt

We demonstrate an LED-based optical wireless link for fixed wireless access applications, at data rates of 1.5 Gbit/s over 50 m. The design is robust against vibration and the infrastructure module can be deployed, e.g., at a lamppost with no...


July 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...


July 2021

Validation of two Techniques for Intraoperative Hyperspectral Human Tissue Determination

Eric Wisotzky, Peter Eisert, Anna Hilsmann, Florian Uecker, Philipp Arens, Benjamin Kossack

In this paper, we introduce and validate two different hyperspectral intraoperative imaging setups and their use for the analysis of optical tissue properties. First, we present an improved multispectral filter-wheel setup integrated into a fully...


July 2021

Focused LRP: Explainable AI for Face Morphing Attack Detection

Clemens Peter Seibold, Peter Eisert, Anna Hilsmann

The task of detecting morphed face images has becomehighly relevant in recent years to ensure the security of automaticverification systems based on facial images, e.g.automated border control gates. Detection methods basedon Deep Neural Networks...


July 2021

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...



Items per page10ǀ20ǀ30
Results 21-30 of 86
<< < 1 2 3 4 5 6 7 8 > >>