Hardness-Based Resampling reduces class recall gaps in balanced datasets by up to 32% on CIFAR-10 and 16% on CIFAR-100 by prioritizing harder samples over random or frequency-based selection.
Balanced Data, Imbalanced Spectra: Unveiling JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 19 Class Disparities with Spectral Imbalance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling
Hardness-Based Resampling reduces class recall gaps in balanced datasets by up to 32% on CIFAR-10 and 16% on CIFAR-100 by prioritizing harder samples over random or frequency-based selection.