A greedy breadth-first search over augmentation operations, with probabilities applied later via Pareto weighting, finds effective policies with far less search compute than AutoAugment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Greedy AutoAugment
A greedy breadth-first search over augmentation operations, with probabilities applied later via Pareto weighting, finds effective policies with far less search compute than AutoAugment.