Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to instance-dependent noises. In this paper, we introduce a novel label noise type called BadLabel, which can significantly degrade the performance of existing LNL algorithms by a large margin. BadLabel is crafted based on the label-flipping attack against standard classification, where specific samples are selected and their labels are flipped to other labels so that the loss values of clean and noisy labels become indistinguishable. To address the challenge posed by BadLabel, we further propose a robust LNL method that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable. Once we select a small set of (mostly) clean labeled data, we can apply the techniques of semi-supervised learning to train the model accurately. Empirically, our experimental results demonstrate that existing LNL algorithms are vulnerable to the newly introduced BadLabel noise type, while our proposed robust LNL method can effectively improve the generalization performance of the model under various types of label noise. The new dataset of noisy labels and the source codes of robust LNL algorithms are available at https://github.com/zjfheart/BadLabels.

翻译：标签噪声学习旨在利用带有噪声标签的训练数据提高模型的泛化能力。为促进实用化标签噪声学习算法的发展，研究者提出了从类别条件噪声到实例依赖噪声等不同类型的标签噪声。本文引入了一种名为BadLabel的新型标签噪声类型，该噪声能显著降低现有标签噪声学习算法的性能。BadLabel基于针对标准分类任务的标签翻转攻击设计，通过选取特定样本并将其标签翻转为其他标签，使干净标签与噪声标签的损失值变得难以区分。为应对BadLabel带来的挑战，我们进一步提出一种鲁棒的标签噪声学习方法，该方法以对抗方式在每个训练周期扰动标签，使干净标签与噪声标签的损失值重新变得可区分。在筛选出一小部分（主要为）干净标注数据后，可结合半监督学习技术精确训练模型。实验结果表明，现有标签噪声学习算法对BadLabel噪声类型均表现出脆弱性，而本文提出的鲁棒标签噪声学习算法能有效提升模型在多种标签噪声类型下的泛化性能。包含噪声标签的新数据集及鲁棒标签噪声学习算法的源代码已开源至https://github.com/zjfheart/BadLabels。