Uncertainty Herding weights coverage by model uncertainty and adapts two parameters so it matches or beats specialized active learning methods at both low and high label budgets.
Gone fishing: Neural active learning with fisher embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Uncertainty Herding: One Active Learning Method for All Label Budgets
Uncertainty Herding weights coverage by model uncertainty and adapts two parameters so it matches or beats specialized active learning methods at both low and high label budgets.