REVIEW 2 cited by
Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational inference to calibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration of uncertainty. The effectiveness of this approach is evaluated on CIFAR-10/100 for recent CNN architectures. Experimental results show, that temperature scaling considerably reduces miscalibration by means of UCE and enables robust rejection of uncertain predictions. The proposed approach can easily be derived from frequentist temperature scaling and yields well-calibrated model uncertainty. It is simple to implement and does not affect the model accuracy.
Forward citations
Cited by 2 Pith papers
-
Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
Rate-In adapts dropout rates per layer and per input at inference by measuring mutual-information loss, improving calibration and sharpening uncertainty estimates in medical imaging tests.
-
Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout
Monte-Carlo Frequency Dropout, which randomly removes frequency components in feature maps, yields better-calibrated uncertainty estimates than standard signal dropout for medical image segmentation.
Discussion (0). Continue with ORCID to comment.