OFAL improves an MNIST classifier from 93.0% to 95.7% test accuracy without oracle labels, by generating uncertain synthetic samples from confident seeds using a VAE and dropout uncertainty.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OFAL: An Oracle-Free Active Learning Framework
OFAL improves an MNIST classifier from 93.0% to 95.7% test accuracy without oracle labels, by generating uncertain synthetic samples from confident seeds using a VAE and dropout uncertainty.