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.
Calibration of Model Uncertainty for Dropout Variational Inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
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.