Aktuelle Publikationen

Juli 2024

AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers

Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer, Sayed M. V. Hatefi, Aakriti Jain

Our new method, AttnLRP, is the first to faithfully and holistically attribute not only input but also latent representations of transformer models with the computational efficiency similar to a single backward pass. We demonstrate that our...


Juli 2024

Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression

Dilyara Bareeva, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer, Frederik Pahde

DNNs are prone to relying on spurious correlations in data, posing risks in critical applications. Post-hoc methods exist to mitigate this without retraining but can globally shift latent features distributions, harming model performance. We...


Juli 2024

Explainable Concept Mappings of MRI: Revealing the Mechanisms Underlying Deep Learning-Based Brain Disease Classification

Christian Tinauer, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer, Reduan Achtibat, Frederik Pahde, Anna Damulina, Maximilian Sackl, Martin Soellradl, Reinhold Schmidt, Stefan Ropele, Christian Langkammer

While recent studies show high accuracy in the classification of Alzheimer's disease using deep neural networks, the underlying learned concepts have not been investigated. We separated Alzheimer's patients (n=117) from normal controls (n=219) by...


Juli 2024

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits

Maximilian Dreyer, Wojciech Samek, Sebastian Lapuschkin, Johanna Vielhaben, Erblina Purelku

Neurons in deep neural networks can act polysemantically, meaning that they encode for multiple (unrelated) features. As such, understanding the inner workings of machine learning models becomes more difficult. We present PURE to turn...


Juli 2024

Model guidance via explanations turns image classifiers into segmentation models

Xiaoyan Yu, Wojciech Samek, Marina M.-C. Höhne, Dagmar Kainmüller, Jannik Franzen

Heatmaps generated on inputs of image classification networks via explainable AI methods have been observed to resemble segmentations of input images in many cases. We apply the "Right for the Right Reason" paradigm of imposing additional losses...


Juni 2024

Unlocking the Potential of Local CSI in Cell-Free Networks with Channel Aging and Fronthaul Delays

Lorenzo Miretti, Slawomir Stanczak

Centralized or distributed precoding? This is perhaps the most heated debate in the Cell-free Massive MIMO literature. However, in this work we argue that the best option may actually be a mix of the two. The reason is that centralized precoding,...


Juni 2024

Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks

Florian Tim Barthel, Peter Eisert, Anna Hilsmann, Wieland Morgenstern, Arian Beckmann

We present a novel approach that combines the high rendering quality of NeRF-based 3D-aware GANs with the flexibility and computational advantages of 3DGS. By training a decoder that maps implicit NeRF representations to explicit 3D Gaussian...


Juni 2024

Towards Bridging the Gap between Near and Far-Field Characterizations of the Wireless Channel

Navneet Agrawal, Slawomir Stanczak, Renato L. G. Cavalcante, Ehsan Tohidi

Exploring near-field propagation is vital for 6G technologies like intelligent reflecting surfaces (IRS). Unlike far-field models, near-field models offer accuracy critical for applications such as beamforming and multiple-access, enhancing...


Juni 2024

Optimized Detection with Analog Beamforming for Monostatic Integrated Sensing and Communication

Rodrigo Hernangómez, Slawomir Stanczak, Renato L. G. Cavalcante, Zoran Utkovski, Jochen Fink

This paper presents an optimization framework for analog beamforming in monostatic integrated sensing and communication (ISAC), which maximizes sensing detection under self-interference cancellation via superiorized projections onto convex...


Juni 2024

Si3N4 Microring-Resonator-Based Integrated Photonic Sensor for Enhanced Label-Free Biofluid Analysis in the 850 nm Optical Band

Jakob Reck, Martin Schell, Moritz Kleinert, Crispin Zawadzki, David de Felipe Mesquida, Martin Kresse, Norbert Keil, Tianwen Qian, Madeleine Weigel, Klara Mihov, Philipp Winklhofer, Csongor Keuer

We present an innovative integrated photonic sensor for point-of-care applications using silicon nitride (Si3N4) tailored for biofluids analysis in the 850nm optical band. With microring resonators (MRR) we detect smallest changes in the...


Ergebnisse pro Seite10ǀ20ǀ30
Ergebnisse 41-50 von 337
<< < 2 3 4 5 6 7 8 9 > >>