论文标题
部分可观测时空混沌系统的无模型预测
Solving The Long-Tailed Problem via Intra- and Inter-Category Balance
论文作者
论文摘要
用于视觉识别的基准数据集假定数据均匀分布，而实际数据集则遵守长尾分布。当前的方法处理了长尾问题，可以通过重新采样或重新加权策略将长尾数据集转换为统一分布。这些方法强调了尾巴类，但忽略了头等阶层中的硬例子，从而导致性能降解。在本文中，我们提出了一种新颖的梯度统一机制，具有类别自适应精度，以使长尾问题中的难度和样本量不平衡取消，该问题通过内部和类别间平衡策略可相应地解决。具体而言，类别内平衡集中在每个类别中的硬示例中以优化决策边界，而类别间平衡旨在通过将每个类别作为一个单位来纠正决策边界的转移。广泛的实验表明，所提出的方法在所有数据集上始终优于其他方法。
Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution. Current approaches handle the long-tailed problem to transform the long-tailed dataset to uniform distribution by re-sampling or re-weighting strategies. These approaches emphasize the tail classes but ignore the hard examples in head classes, which result in performance degradation. In this paper, we propose a novel gradient harmonized mechanism with category-wise adaptive precision to decouple the difficulty and sample size imbalance in the long-tailed problem, which are correspondingly solved via intra- and inter-category balance strategies. Specifically, intra-category balance focuses on the hard examples in each category to optimize the decision boundary, while inter-category balance aims to correct the shift of decision boundary by taking each category as a unit. Extensive experiments demonstrate that the proposed method consistently outperforms other approaches on all the datasets.
