no code implementations • 23 Dec 2023 • Lokesh Veeramacheneni, Moritz Wolter, Juergen Gall
In response, we propose a new frequency band-based quality metric, which opens a door into the frequency domain yet, at the same time, preserves spatial aspects of the data.
no code implementations • 11 Nov 2022 • Lokesh Veeramacheneni, Matias Valdenegro-Toro
We observed that Deep Ensembles out perform Flipout model in OOD detection with greater AUROC scores for both datasets.
1 code implementation • 3 Jun 2022 • Lokesh Veeramacheneni, Moritz Wolter, Reinhard Klein, Jochen Garcke
We introduce canonical weight normalization for convolutional neural networks.