Reconstruction error ratios from class-wise autoencoders correlate with dataset classification difficulty and detect mislabeled images on hard datasets.
Title resolution pending
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
-
Class-wise Autoencoders Measure Classification Difficulty And Detect Label Mistakes
Reconstruction error ratios from class-wise autoencoders correlate with dataset classification difficulty and detect mislabeled images on hard datasets.