Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Jan Kronenberger"'
Autor:
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
Publikováno v:
Deep Neural Networks and Data for Automated Driving ISBN: 9783031012327
Fingscheidt, Gottschalk et al. (Hg.): Deep Neural Networks and Data for Automated Driving. Robustness, Uncertainty Quantification, and Insights Towards Safety
Fingscheidt, Gottschalk et al. (Hg.): Deep Neural Networks and Data for Automated Driving. Robustness, Uncertainty Quantification, and Insights Towards Safety
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a97320425a5b7fac20b0272cdc9fe19b
https://doi.org/10.1007/978-3-031-01233-4_1
https://doi.org/10.1007/978-3-031-01233-4_1
Publikováno v:
CVPR Workshops
In this paper, we propose a method for post-hoc ex-plainability of black-box models. The key component of the semantic and quantitative local explanation is a knowledge distillation (KD) process which is used to mimic the teacher’s behavior by mean
Publikováno v:
MobileHCI
In automated vehicles, it is essential to feedforward motion intentions to users so that they understand the vehicle’s actions. Otherwise, non-transparency limits situation awareness and leads to mistrust. In this work, we are communicating the veh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cddd89d2fdccf933502ce25a063e89bb
https://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&origin=inward&scp=85117354203
https://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&origin=inward&scp=85117354203
Modern neural networks have found to be miscalibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision. Recent work has introduced methods for post-hoc confidence calibratio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9aa998d6f5bed685c9e0059056751121
Publikováno v:
CVPR Workshops
Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods for classification, the field of
Autor:
Jan Kronenberger, Anselm Haselhoff
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2018 ISBN: 9783030014230
ICANN (3)
ICANN (3)
Detecting and classifying traffic signs is a very import step to future autonomous driving. In contrast to earlier approaches with handcrafted features, modern neural networks learn the representation of the classes themselves. Current convolutional
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02dfe4df127c8d703cd1410798498a6a
https://doi.org/10.1007/978-3-030-01424-7_4
https://doi.org/10.1007/978-3-030-01424-7_4
Publikováno v:
ICIA
To improve the automation of metal sheet production these sheets have to be tracked during the processing steps. This is preferably done by video optical tracking. To recognize the metal sheets each of them has an unique ID imprinted. This paper desc