no code implementations • 5 Mar 2024 • Jan E. Gerken, Pan Kessel
We demonstrate that deep ensembles are secretly equivariant models.
1 code implementation • 14 Jul 2023 • Oscar Carlsson, Jan E. Gerken, Hampus Linander, Heiner Spieß, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson
High-resolution wide-angle fisheye images are becoming more and more important for robotics applications such as autonomous driving.
1 code implementation • 10 Jun 2022 • Ann-Kathrin Dombrowski, Jan E. Gerken, Klaus-Robert Müller, Pan Kessel
Counterfactuals can explain classification decisions of neural networks in a human interpretable way.
1 code implementation • 8 Feb 2022 • Jan E. Gerken, Oscar Carlsson, Hampus Linander, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson
We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with an increasing amount of data augmentation.
no code implementations • 28 May 2021 • Jan E. Gerken, Jimmy Aronsson, Oscar Carlsson, Hampus Linander, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson
We also discuss group equivariant neural networks for homogeneous spaces $\mathcal{M}=G/K$, which are instead equivariant with respect to the global symmetry $G$ on $\mathcal{M}$.