Random-noise pretraining calibrates small networks' confidence to chance level before data training, reducing expected calibration error and improving OOD detection on CIFAR-10/SVHN.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Pretraining with random noise for uncertainty calibration
Random-noise pretraining calibrates small networks' confidence to chance level before data training, reducing expected calibration error and improving OOD detection on CIFAR-10/SVHN.