3 papers
cs.CV2020
A simple way to make neural networks robust against diverse image corruptions
Evgenia Rusak, Lukas Schott, Roland S. Zimmermann +4
The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image…
cs.CV2019
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos +5
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide…
physics.optics2019
Enhancement of and interference among higher order multipole transitions in molecules near a plasmonic nanoantenna
Evgenia Rusak, Jakob Straubel, Piotr Gładysz +6
Spontaneous emission of quantum emitters can be modified by engineering their optical environment. This allows a resonant nanoantenna to significantly modify the radiative properti…