1 code implementation • 20 Mar 2020 • Andres C. Rodriguez, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner
We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets.
no code implementations • 19 Sep 2018 • Andres C. Rodriguez, Jan D. Wegner
This task is hard due to the cluttered nature of scenes where different object categories occur.
no code implementations • 27 Jan 2018 • Andres C. Rodriguez, Tomasz Kacprzak, Aurelien Lucchi, Adam Amara, Raphael Sgier, Janis Fluri, Thomas Hofmann, Alexandre Réfrégier
Computational models of the underlying physical processes, such as classical N-body simulations, are extremely resource intensive, as they track the action of gravity in an expanding universe using billions of particles as tracers of the cosmic matter distribution.