On the Importance of Feature Separability in Predicting Out-Of-Distribution Error.

Renchunzi Xie Hongxin Wei Yuzhou Cao Lei Feng Bo An

Published in: CoRR (2023)

Keyphrases

error rate
image features
data distribution
feature distributions
feature vectors
uniformly distributed
random variables
expected error
power law
relative importance
error analysis
error bounds
learning algorithm
dimensionality reduction
probability distribution
hidden markov models
decision trees
computer vision