activity
20242026
collaborators

10 papers

cs.LG2026

EXCODER: EXplainable Classification Of DiscretE time series Representations

Yannik Hahn, Antonin Königsfeld, Hasan Tercan +1

Deep learning has significantly improved time series classification, yet the lack of explainability in these models remains a major challenge. While Explainable AI (XAI) techniques…

cs.CV2025

Graph Query Networks for Object Detection with Automotive Radar

Loveneet Saini, Hasan Tercan, Tobias Meisen

Object detection with 3D radar is essential for 360-degree automotive perception, but radar's long wavelengths produce sparse and irregular reflections that challenge traditional g…

cs.CV2025

Efficient Inter-Task Attention for Multitask Transformer Models

Christian Bohn, Thomas Kurbiel, Klaus Friedrichs +2

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, howev…

cs.LG2025

Out of Distribution Detection for Efficient Continual Learning in Quality Prediction for Arc Welding

Yannik Hahn, Jan Voets, Antonin Koenigsfeld +2

Modern manufacturing relies heavily on fusion welding processes, including gas metal arc welding (GMAW). Despite significant advances in machine learning-based quality prediction,…

cs.CV2025

Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR

Adwait Chandorkar, Hasan Tercan, Tobias Meisen

Recent advancements in LiDAR-based 3D object detection have significantly accelerated progress toward the realization of fully autonomous driving in real-world environments. Despit…

cs.CV2025

Detection Transformers Under the Knife: A Neuroscience-Inspired Approach to Ablations

Nils Hütten, Florian Hölken, Hasan Tercan +1

In recent years, Explainable AI has gained traction as an approach to enhancing model interpretability and transparency, particularly in complex models such as detection transforme…