A new fine-grained benchmark dataset of ostracod images shows that existing robust-learning and label-correction methods do not outperform cross-entropy or a naive ensemble baseline.
Holmes and Allan R
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
-
Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
A new fine-grained benchmark dataset of ostracod images shows that existing robust-learning and label-correction methods do not outperform cross-entropy or a naive ensemble baseline.