For learning with noisy labels, the transition matrix, which explicitly models the relation between noisy label distribution and clean label distribution, has been utilized to achieve the statistical consistency of either the classifier or the risk. Previous researches have focused more on how to estimate this transition matrix well, rather than how to utilize it. We propose good utilization of the transition matrix is crucial and suggest a new utilization method based on resampling, coined RENT. Specifically, we first demonstrate current utilizations can have potential limitations for implementation. As an extension to Reweighting, we suggest the Dirichlet distribution-based per-sample Weight Sampling (DWS) framework, and compare reweighting and resampling under DWS framework. With the analyses from DWS, we propose RENT, a REsampling method with Noise Transition matrix. Empirically, RENT consistently outperforms existing transition matrix utilization methods, which includes reweighting, on various benchmark datasets. Our code is available at \url{https://github.com/BaeHeeSun/RENT}.

翻译：针对噪声标签学习问题，转移矩阵通过显式建模噪声标签分布与干净标签分布之间的关系，已被用于实现分类器或风险函数的统计一致性。以往研究更关注如何准确估计该转移矩阵，而非如何有效利用它。我们提出，对转移矩阵的良好利用至关重要，并基于重采样思想提出了一种新方法——RENT。具体而言，我们首先指出现有利用方法在实现中可能存在潜在局限。作为重加权方法的延伸，我们提出基于狄利克雷分布的逐样本权重采样（DWS）框架，并在该框架下比较了重加权与重采样的效果。基于DWS框架的分析，我们提出了RENT——一种基于噪声转移矩阵的重采样方法。实验表明，在多个基准数据集上，RENT始终优于现有转移矩阵利用方法（包括重加权）。我们的代码开源在：\url{https://github.com/BaeHeeSun/RENT}。