activity
20202024
most citedScalable Bayesian neural networks by layer-wise input augmentation

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2024

Improving robustness to corruptions with multiplicative weight perturbations

Trung Trinh, Markus Heinonen, Luigi Acerbi +1

Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to…