Details
| Original language | English |
|---|---|
| Publication status | E-pub ahead of print - 20 Jun 2020 |
Abstract
Keywords
- cs.LG, stat.ML
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2020.
Research output: Working paper/Preprint › Preprint
}
TY - UNPB
T1 - Calibration of Model Uncertainty for Dropout Variational Inference
AU - Laves, Max-Heinrich
AU - Ihler, Sontje
AU - Kortmann, Karl-Philipp
AU - Ortmaier, Tobias
PY - 2020/6/20
Y1 - 2020/6/20
N2 - The model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. In this paper, different logit scaling methods are extended to dropout variational inference to recalibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration. The effectiveness of recalibration is evaluated on CIFAR-10/100 and SVHN for recent CNN architectures. Experimental results show that logit scaling considerably reduce miscalibration by means of UCE. Well-calibrated uncertainty enables reliable rejection of uncertain predictions and robust detection of out-of-distribution data.
AB - The model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. In this paper, different logit scaling methods are extended to dropout variational inference to recalibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration. The effectiveness of recalibration is evaluated on CIFAR-10/100 and SVHN for recent CNN architectures. Experimental results show that logit scaling considerably reduce miscalibration by means of UCE. Well-calibrated uncertainty enables reliable rejection of uncertain predictions and robust detection of out-of-distribution data.
KW - cs.LG
KW - stat.ML
M3 - Preprint
BT - Calibration of Model Uncertainty for Dropout Variational Inference
ER -