MetaErr introduces a meta-model that forecasts per-sample prediction errors in deep neural networks solely from base model performance observations, outperforming baselines and boosting pseudo-labeling on three computer vision datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MetaErr: Towards Predicting Error Patterns in Deep Neural Networks
MetaErr introduces a meta-model that forecasts per-sample prediction errors in deep neural networks solely from base model performance observations, outperforming baselines and boosting pseudo-labeling on three computer vision datasets.