Jonas Löhdefink

17 papers C 3Journal 8Unranked 6
YearRankTypeTitle / Venue / Authors
2022 — conf
Adaptive Bitrate Quantization Scheme Without Codebook for Learned Image Compression.
CVPR Workshops
Jonas Löhdefink, Jonas Sitzmann, Andreas Bär, Tim Fingscheidt
2022 J jnl
Improving Performance of Semantic Segmentation CycleGANs by Noise Injection into the Latent Segmentation Space.
CoRR
Jonas Löhdefink, Tim Fingscheidt
2022 — conf
Joint Prediction of Amodal and Visible Semantic Segmentation for Automated Driving.
ECCV Workshops (1)
Jasmin Breitenstein, Jonas Löhdefink, Tim Fingscheidt
2022 — conf
Performance Prediction for Semantic Segmentation by a Self-Supervised Image Reconstruction Decoder.
CVPR Workshops
Andreas Bär, Marvin Klingner, Jonas Löhdefink, Fabian Hüger, Peter Schlicht, Tim Fingscheidt
2021 C conf
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving.
IV
Florian Heidecker, Jasmin Breitenstein, Kevin Rösch, Jonas Löhdefink, Maarten Bieshaar, Christoph Stiller, Tim Fingscheidt, Bernhard Sick
2021 J jnl
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving.
CoRR
Florian Heidecker, Jasmin Breitenstein, Kevin Rösch, Jonas Löhdefink, Maarten Bieshaar, Christoph Stiller, Tim Fingscheidt, Bernhard Sick
2021 J jnl
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety.
CoRR
Sebastian Houben, Stephanie Abrecht, Maram Akila, Andreas Bär, Felix Brockherde, Patrick Feifel, Tim Fingscheidt, Sujan Sai Gannamaneni, Seyed Eghbal Ghobadi, Ahmed Hammam, Anselm Haselhoff, Felix Hauser, Christian Heinzemann, Marco Hoffmann, Nikhil Kapoor, Falk Kappel, Marvin Klingner, Jan Kronenberger, Fabian Küppers, Jonas Löhdefink, Michael Mlynarski, Michael Mock, Firas Mualla, Svetlana Pavlitskaya, Maximilian Poretschkin, Alexander Pohl, Varun Ravi Kumar, Julia Rosenzweig, Matthias Rottmann, Stefan Rüping, Timo Sämann, Jan David Schneider, Elena Schulz, Gesina Schwalbe, Joachim Sicking, Toshika Srivastava, Serin Varghese, Michael Weber, Sebastian Wirkert, Tim Wirtz, Matthias Woehrle
2021 J jnl
The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing.
CoRR
Andreas Bär, Jonas Löhdefink, Nikhil Kapoor, Serin J. Varghese, Fabian Hüger, Peter Schlicht, Tim Fingscheidt
2021 J jnl
The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing.
IEEE Signal Process. Mag.
Andreas Bär, Jonas Löhdefink, Nikhil Kapoor, Serin Varghese, Fabian Hüger, Peter Schlicht, Tim Fingscheidt
2020 — conf
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs.
CSCS
Nikhil Kapoor, Chun Yuan, Jonas Löhdefink, Roland Zimmermann, Serin Varghese, Fabian Hüger, Nico M. Schmidt, Peter Schlicht, Tim Fingscheidt
2020 J jnl
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs.
CoRR
Nikhil Kapoor, Chun Yuan, Jonas Löhdefink, Roland Zimmermann, Serin Varghese, Fabian Hüger, Nico M. Schmidt, Peter Schlicht, Tim Fingscheidt
2020 C conf
Focussing Learned Image Compression to Semantic Classes for V2X Applications.
IV
Jonas Löhdefink, Andreas Bär, Nico M. Schmidt, Fabian Hüger, Peter Schlicht, Tim Fingscheidt
2020 — conf
Scalar and Vector Quantization for Learned Image Compression: A Study on the Effects of MSE and GAN Loss in Various Spaces.
ITSC
Jonas Löhdefink, Fabian Hüger, Peter Schlicht, Tim Fingscheidt
2020 — conf
Self-Supervised Domain Mismatch Estimation for Autonomous Perception.
CVPR Workshops
Jonas Löhdefink, Justin Fehrling, Marvin Klingner, Fabian Hüger, Peter Schlicht, Nico M. Schmidt, Tim Fingscheidt
2020 J jnl
Self-Supervised Domain Mismatch Estimation for Autonomous Perception.
CoRR
Jonas Löhdefink, Justin Fehrling, Marvin Klingner, Fabian Hüger, Peter Schlicht, Nico M. Schmidt, Tim Fingscheidt
2019 J jnl
GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation.
CoRR
Jonas Löhdefink, Andreas Bär, Nico M. Schmidt, Fabian Hüger, Peter Schlicht, Tim Fingscheidt
2019 C conf
On Low-Bitrate Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation.
IV
Jonas Löhdefink, Andreas Bär, Nico M. Schmidt, Fabian Hüger, Peter Schlicht, Tim Fingscheidt