Reviving Undersampling for Long-Tailed Learning. (arXiv:2401.16811v1 [cs.CV])

The training datasets used in long-tailed recognition are extremely
unbalanced, resulting in significant variation in per-class accuracy across
categories. Prior works mostly used average accuracy to evaluate their
algorithms, which easily ignores those worst-performing categories. In this
paper, we aim to enhance the accuracy of the worst-performing categories and
utilize the harmonic mean and geometric mean to assess the model's performance.
We revive the balanced undersampling idea to achieve this goal. In few-shot
learning, balanced subsets are few-shot and will …

accuracy aim algorithms arxiv class cs.cv datasets mean paper per prior recognition training undersampling variation