REVIEW 2 cited by
Calibration of Model Uncertainty 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
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.
Forward citations
Cited by 2 Pith papers
-
Confidence-Uncertainty Boundary Calibration for Bayesian Deep Learning in Medical Image Analysis
A confidence-entropy boundary curve loss plus dual temperature scaling improves AvU and reduces BCCE on three medical imaging tasks, though evaluation is internally referenced to the same curve.
-
Uncertainty-aware Test-Time Training (UT$^3$) for Efficient On-the-fly Domain Adaptive Dense Regression
UT3 selects keyframes via entropy of an uncertainty-aware masked-autoencoder self-supervision head, skipping test-time training on most frames and cutting inference time by about 70% with similar accuracy.
Discussion (0). Continue with ORCID to comment.