activity
20192021
most citedGAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation

9 citations · 14 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV2021

Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis

Julia Rosenzweig, Eduardo Brito, Hans-Ulrich Kobialka +8

Many machine learning applications can benefit from simulated data for systematic validation - in particular if real-life data is difficult to obtain or annotate. However, since si…

cs.CV20205 cited

A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs

Nikhil Kapoor, Chun Yuan, Jonas Löhdefink +6

Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional ne…

cs.CV2020

Self-Supervised Domain Mismatch Estimation for Autonomous Perception

Jonas Löhdefink, Justin Fehrling, Marvin Klingner +4

Autonomous driving requires self awareness of its perception functions. Technically spoken, this can be realized by observers, which monitor the performance indicators of various p…

cs.LG2019

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

Felix Assion, Peter Schlicht, Florens Greßner +4

Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challen…

cs.CV20199 cited

GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation

Jonas Löhdefink, Andreas Bär, Nico M. Schmidt +3

The high amount of sensors required for autonomous driving poses enormous challenges on the capacity of automotive bus systems. There is a need to understand tradeoffs between bitr…