A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning. paper with code

Open paper
Benchmark Model Rank Results
long-tail-learning-on-cifar-10-lt-r-10VS + ADRW + TLA#5Error Rate: 8.18
long-tail-learning-on-cifar-10-lt-r-100VS + ADRW + TLA#7Error Rate: 13.58
long-tail-learning-on-cifar-100-lt-r-10VS + ADRW + TLA#11Error Rate: 34.41
long-tail-learning-on-cifar-100-lt-r-100VS + ADRW + TLA#19Error Rate: 46.95

Rank counts only results with a code link.