Accepted Papers

Best Paper

An Unsupervised Temporal Consistency (TC) Loss to Improve the Performance of Semantic Segmentation Networks (ID 5)

Serin Varghese (Volkswagen AG); Sharat Gujamagadi (Volkswagen AG); Marvin Klingner (Technische Universität Braunschweig ); Nikhil Kapoor (Volkswagen AG); Andreas Bär (Technische Universität Braunschweig); Jan David Schneider (Volkswagen AG); Kira Maag (University of Wuppertal); Peter Schlicht (Volkswagen Group Research); Fabian Hüger (Volkswagen AG); Tim Fingscheidt (Technische Universität Braunschweig)

Long Orals

Adversarial Robust Model Compression using In-Train Pruning (ID 1)

Manoj Rohit Vemparala (BMW Group); Nael Fasfous (Technical University of Munich); Alexander Frickenstein (BMW Group); Sreetama Sarkar (BMW Group); Qi Zhao (Karlsruhe Institute of Technology); Sabine Kuhn (BMW Group); Lukas Frickenstein (BMW Group); Anmol Singh (BMW Group); Christian Unger (BMW); Naveen Shankar Nagaraja (BMW Group); Christian Wressnegger (Karlsruhe Institute of Technology); WALTER STECHELE (Technical University of Munich, Germany)

Reevaluating the Safety Impact of Inherent Interpretability on Deep Neural Networks for Pedestrian Detection (ID 2)

Patrick Feifel (Stellantis, Opel Automobile GmbH); Frank Bonarens (Stellantis, Opel Automobile GmbH); Frank Köster (Deutsches Zentrum für Luft- und Raumfahrt)

Sparse Activation Maps for Interpreting 3D Object Detection (ID 3)

Qiuxiao Chen (Utah State University); Pengfei Li (UC Riverside); Meng Xu (Utah State University); Xiaojun Qi (USU)

Improving Online Performance Prediction for Semantic Segmentation (ID 4)

Marvin Klingner (Technische Universität Braunschweig); Andreas Bär (Technische Universität Braunschweig); Marcel A Mross (Technische Universität Braunschweig); Tim Fingscheidt (Technische Universität Braunschweig)

An Unsupervised Temporal Consistency (TC) Loss to Improve the Performance of Semantic Segmentation Networks (ID 5)

Short Orals

From Evaluation to Verification: Towards Task-oriented Relevance Metrics for Pedestrian Detection in Safety-critical Domains (ID 6)

Maria Lyssenko (Robert Bosch GmbH); Christoph D Gladisch (Robert Bosch GmbH); Christian Heinzemann (Robert Bosch GmbH); Matthias Woehrle (Robert Bosch GmbH); Rudolph Triebel (German Aerospace Center (DLR))

Development Methodologies for Safety Critical Machine Learning Applications in the Automotive Domain: A Survey (ID 7)

Martin Rabe (TU Ilmenau); Stefan Milz (Spleenlab.ai / Ilmenau University); Patrick Maeder (Technische Universität Ilmenau)

Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders (ID 8)

Felix Möller (Universität Kassel); Diego D Botache (University of Kassel); Denis Huseljic (University of Kassel); Florian Heidecker (University of Kassel); Maarten Bieshaar (University of Kassel); Bernhard Sick (University of Kassel)

Boosting Adversarial Robustness using Feature Level Stochastic Smoothing (ID 9)

Sravanti Addepalli (Indian Institute of Science); Samyak Jain (Indian Institute of Technology (BHU), Varanasi); Gaurang Sriramanan (Indian Institute of Science); Venkatesh Babu RADHAKRISHNAN (Indian Institute of Science)

SafeSO: Interpretable and Explainable Deep Learning Approach for Seat Occupancy Classification in Vehicle Interior (ID 10)

Joanna Jaworek-Korjakowska (AGH University of Science and Technology); Aleksander Kostuch (AGH University of Science and Technology); Pawel Skruch (AGH University of Science and Technology)

Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities (ID 11)

Julia Rosenzweig (Fraunhofer IAIS); Joachim Sicking (Fraunhofer IAIS); Sebastian Houben (Fraunhofer Institute for Intelligent Analysis and Information Systems); Michael Mock (Fraunhofer, DE); Maram Akila (Fraunhofer IAIS)

Towards Black-Box Explainability with Gaussian Discriminant Knowledge Distillation (ID 12)

Anselm Haselhoff (Ruhr West University of Applied Sciences); Jan Kronenberger (Ruhr West University of Applied Sciences)*; Fabian Küppers (Ruhr West University of Applied Sciences); Jonas Schneider (Elektronische Fahrwerksysteme GmbH)

Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation (ID 13)

Linara Adilova (Fraunhofer IAIS); Elena Schulz (Fraunhofer IAIS); Maram Akila (Fraunhofer IAIS); Sebastian Houben (Fraunhofer Institute for Intelligent Analysis and Information Systems); Jan David Schneider (Volkswagen AG); Fabian Hüger (Volkswagen AG); Tim Wirtz (Fraunhofer IAIS)

Detecting Anomalies in Semantic Segmentation with Prototypes (ID 14)

Dario Fontanel (Politecnico di Torino); Fabio Cermelli (Politecnico di Torino); Massimiliano Mancini (University of Tübingen); Barbara Caputo (Politecnico di Torino)

Simulation Driven Design and Test for Safety of AI Based Autonomous Vehicles (ID 15)

Vasu Singh (NVIDIA); Siva Kumar Sastry Hari (NVIDIA); Timothy Tsai (NVIDIA); Mandar Pitale (NVIDIA)