Striking the Right Balance with Uncertainty

CVPR, 2019.

Cited by: 15|Bibtex|Views16|Links
EI

Abstract:

Learning unbiased models on imbalanced datasets is a significant challenge. Rare classes tend to get a concentrated representation in the classification space which hampers the generalization of learned boundaries to new test examples. In this paper, we demonstrate that the Bayesian uncertainty estimates directly correlate with the rarity...More

Code:

Data:

Your rating :
0

 

Tags
Comments