Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Hueger, Fabian"'
Semantic segmentation networks have achieved significant success under the assumption of independent and identically distributed data. However, these networks often struggle to detect anomalies from unknown semantic classes due to the limited set of
Externí odkaz:
http://arxiv.org/abs/2409.17330
Autor:
Chan, Robin, Dardashti, Radin, Osinski, Meike, Rottmann, Matthias, Brüggemann, Dominik, Rücker, Cilia, Schlicht, Peter, Hüger, Fabian, Rummel, Nikol, Gottschalk, Hanno
Publikováno v:
AI and Ethics (2023)
Deep neural networks (DNN) have made impressive progress in the interpretation of image data, so that it is conceivable and to some degree realistic to use them in safety critical applications like automated driving. From an ethical standpoint, the A
Externí odkaz:
http://arxiv.org/abs/2206.04776
Autor:
Sicking, Joachim, Akila, Maram, Schneider, Jan David, Hüger, Fabian, Schlicht, Peter, Wirtz, Tim, Wrobel, Stefan
Uncertainty estimation bears the potential to make deep learning (DL) systems more reliable. Standard techniques for uncertainty estimation, however, come along with specific combinations of strengths and weaknesses, e.g., with respect to estimation
Externí odkaz:
http://arxiv.org/abs/2204.13963
Autor:
Rosenzweig, Julia, Brito, Eduardo, Kobialka, Hans-Ulrich, Akila, Maram, Schmidt, Nico M., Schlicht, Peter, Schneider, Jan David, Hüger, Fabian, Rottmann, Matthias, Houben, Sebastian, Wirtz, Tim
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 simulations are prone to domain shift w.r.t. real-life data, it is cruci
Externí odkaz:
http://arxiv.org/abs/2106.05549
Autor:
Adilova, Linara, Schulz, Elena, Akila, Maram, Houben, Sebastian, Schneider, Jan David, Hueger, Fabian, Wirtz, Tim
Data-driven sensor interpretation in autonomous driving can lead to highly implausible predictions as can most of the time be verified with common-sense knowledge. However, learning common knowledge only from data is hard and approaches for knowledge
Externí odkaz:
http://arxiv.org/abs/2104.09254
Autor:
von Rueden, Laura, Wirtz, Tim, Hueger, Fabian, Schneider, Jan David, Piatkowski, Nico, Bauckhage, Christian
Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness, which motivates the thorough validation of learned models. However, current validation approaches mostly require ground truth data and are thus bot
Externí odkaz:
http://arxiv.org/abs/2104.07538
Autor:
Bär, Andreas, Löhdefink, Jonas, Kapoor, Nikhil, Varghese, Serin J., Hüger, Fabian, Schlicht, Peter, Fingscheidt, Tim
Enabling autonomous driving (AD) can be considered one of the biggest challenges in today's technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment perception
Externí odkaz:
http://arxiv.org/abs/2101.03924
Autor:
Sicking, Joachim, Kister, Alexander, Fahrland, Matthias, Eickeler, Stefan, Hüger, Fabian, Rüping, Stefan, Schlicht, Peter, Wirtz, Tim
Statistical models are inherently uncertain. Quantifying or at least upper-bounding their uncertainties is vital for safety-critical systems such as autonomous vehicles. While standard neural networks do not report this information, several approache
Externí odkaz:
http://arxiv.org/abs/2101.02974
Autor:
Maag, Kira, Rottmann, Matthias, Varghese, Serin, Hueger, Fabian, Schlicht, Peter, Gottschalk, Hanno
Instance segmentation with neural networks is an essential task in environment perception. In many works, it has been observed that neural networks can predict false positive instances with high confidence values and true positives with low ones. Thu
Externí odkaz:
http://arxiv.org/abs/2012.07504
Autor:
Kapoor, Nikhil, Bär, Andreas, Varghese, Serin, Schneider, Jan David, Hüger, Fabian, Schlicht, Peter, Fingscheidt, Tim
Despite recent advancements, deep neural networks are not robust against adversarial perturbations. Many of the proposed adversarial defense approaches use computationally expensive training mechanisms that do not scale to complex real-world tasks su
Externí odkaz:
http://arxiv.org/abs/2012.01558