A per-class Gaussian process over DNN features, scored by KL divergence between predictive distributions, detects out-of-distribution images using only in-distribution data to set the threshold.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Uncertainty-Aware Out-of-Distribution Detection with Gaussian Processes
A per-class Gaussian process over DNN features, scored by KL divergence between predictive distributions, detects out-of-distribution images using only in-distribution data to set the threshold.