Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a label-reliable subset for model training. In this paper, we empirically reveal that existing sample selection methods suffer from both data and training bias that are represented as imbalanced selected sets and accumulation errors in practice, respectively. However, only the training bias was handled in previous studies. To address this limitation, we propose a noIse-Tolerant Expert Model (ITEM) for debiased learning in sample selection. Specifically, to mitigate the training bias, we design a robust network architecture that integrates with multiple experts. Compared with the prevailing double-branch network, our network exhibits better performance of selection and prediction by ensembling these experts while training with fewer parameters. Meanwhile, to mitigate the data bias, we propose a mixed sampling strategy based on two weight-based data samplers. By training on the mixture of two class-discriminative mini-batches, the model mitigates the effect of the imbalanced training set while avoiding sparse representations that are easily caused by sampling strategies. Extensive experiments and analyses demonstrate the effectiveness of ITEM. Our code is available at this url \href{https://github.com/1998v7/ITEM}{ITEM}.

翻译：带噪声标签的学习旨在确保在标签受损的训练集上实现模型泛化。样本选择策略通过选择标签可靠的子集进行模型训练，取得了良好的性能。本文通过实证研究发现，现有的样本选择方法在训练过程中分别受到数据和训练偏差的影响，具体表现为不平衡的选择集和累积误差。然而，以往的研究仅处理了训练偏差。为解决这一局限性，我们提出了一种噪声容忍专家模型（ITEM）用于样本选择中的去偏学习。具体而言，为缓解训练偏差，我们设计了一种集成多个专家的鲁棒网络架构。与目前主流的双分支网络相比，我们的网络通过集成这些专家，在训练参数更少的同时，在选择和预测方面表现出更优的性能。同时，为缓解数据偏差，我们提出了一种基于两个权重数据采样器的混合采样策略。通过在这两类判别性小批量数据的混合集上训练，该模型减轻了不平衡训练集的影响，同时避免了采样策略易导致的稀疏表示问题。大量实验和分析证明了ITEM的有效性。我们的代码可在以下网址获取：\href{https://github.com/1998v7/ITEM}{ITEM}。