Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean and noisy samples. These methods have gained notable success. However, unlike cherry-picked data, existing approaches often cannot perform well when facing imbalanced datasets, a common scenario in the real world. We thoroughly investigate this phenomenon and point out two major issues that hinder the performance, i.e., \emph{inter-class loss distribution discrepancy} and \emph{misleading predictions due to uncertainty}. The first issue is that existing methods often perform class-agnostic noise modeling. However, loss distributions show a significant discrepancy among classes under class imbalance, and class-agnostic noise modeling can easily get confused with noisy samples and samples in minority classes. The second issue refers to that models may output misleading predictions due to epistemic uncertainty and aleatoric uncertainty, thus existing methods that rely solely on the output probabilities may fail to distinguish confident samples. Inspired by our observations, we propose an Uncertainty-aware Label Correction framework~(ULC) to handle label noise on imbalanced datasets. First, we perform epistemic uncertainty-aware class-specific noise modeling to identify trustworthy clean samples and refine/discard highly confident true/corrupted labels. Then, we introduce aleatoric uncertainty in the subsequent learning process to prevent noise accumulation in the label noise modeling process. We conduct experiments on several synthetic and real-world datasets. The results demonstrate the effectiveness of the proposed method, especially on imbalanced datasets.
翻译:针对标签噪音的学习是保证深层神经网络可靠性能的一个重要议题。最近的研究通常是指动态噪音模型,以模型产出的不确定性概率和损失值来进行动态噪音模型,然后将清洁和吵闹的样本分离出来。这些方法取得了显著的成功。然而,与樱桃所选数据不同,现有方法在面对不平衡的数据集时往往无法很好地发挥作用,这是现实世界中常见的场景。我们彻底调查了这一现象,并指出了妨碍性能的两大问题,即:噪音的累积性(emph{跨类损失分布差异 ) 和 memph{误差预测由于不确定性而导致的不确定性。第一个问题是,现有方法往往使用模型的不确定性模型和误差的预测值。现有的方法可能无法辨别可靠的样本。然而,在我们的观察中,损失分布显示阶级不平衡的类别之间存在很大的差异,而等级噪音模型的模型则很容易被混杂地混淆。