Mixup improves neural network generalization by training on convex combinations of example pairs and their labels instead of standard empirical risk minimization.
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
2017 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
mixup: Beyond Empirical Risk Minimization
Mixup improves neural network generalization by training on convex combinations of example pairs and their labels instead of standard empirical risk minimization.