SLA detects noisy labels task-agnostically by standardizing and aggregating validation losses across repeated cross-validation folds, generalizing hard-counting into a continuous estimator that outperforms baselines on fundus data.
O2u-net: A simple noisy label detection approach for deep neural networks
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.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation
SLA detects noisy labels task-agnostically by standardizing and aggregating validation losses across repeated cross-validation folds, generalizing hard-counting into a continuous estimator that outperforms baselines on fundus data.