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 surely under-fit, hence it is not used in modern long-tailed learning. But, we find that it produces a more equitable distribution of accuracy across categories with much higher harmonic and geometric mean accuracy, and, but lower average accuracy. Moreover, we devise a straightforward model ensemble strategy, which does not result in any additional overhead and achieves improved harmonic and geometric mean while keeping the average accuracy almost intact when compared to state-of-the-art long-tailed learning methods. We validate the effectiveness of our approach on widely utilized benchmark datasets for long-tailed learning. Our code is at \href{https://github.com/yuhao318/BTM/}{https://github.com/yuhao318/BTM/}.

翻译：长尾识别任务中使用的训练数据集极度不平衡，导致各类别的分类准确率存在显著差异。以往研究大多采用平均准确率评估算法性能，这容易忽略表现最差的类别。本文旨在提升最差类别的准确率，并采用调和平均数与几何平均数评估模型性能。我们通过重振平衡欠采样方法来实现这一目标。在小样本学习中，平衡子集因样本量极少必然导致欠拟合，因此现代长尾学习技术中很少使用该方法。但我们发现，该方法能更均衡地分配各类别准确率，使调和平均与几何平均准确率显著提升，尽管平均准确率略有下降。此外，我们设计了一种简洁的模型集成策略，无需引入任何额外计算开销，在保持平均准确率基本不变的前提下，与现有最先进的长尾学习方法相比，进一步提升了调和平均与几何平均指标。我们在广泛使用的长尾学习基准数据集上验证了方法的有效性。代码开源地址为：\href{https://github.com/yuhao318/BTM/}{https://github.com/yuhao318/BTM/}。