1 citations · 1 across the 4 of their papers we have counts for
4 papers
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…
Input-gradient space particle inference for neural network ensembles
Trung Trinh, Markus Heinonen, Luigi Acerbi +1
Deep Ensembles (DEs) demonstrate improved accuracy, calibration and robustness to perturbations over single neural networks partly due to their functional diversity. Particle-based…
Tackling covariate shift with node-based Bayesian neural networks
Trung Trinh, Markus Heinonen, Luigi Acerbi +1
Bayesian neural networks (BNNs) promise improved generalization under covariate shift by providing principled probabilistic representations of epistemic uncertainty. However, weigh…
Scalable Bayesian neural networks by layer-wise input augmentation
Trung Trinh, Samuel Kaski, Markus Heinonen
We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning. Standard Bayesian approach to deep learning requires…