Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a new approach for learning from noisy labels (LNL) via post-training, which can significantly improve the generalization performance of any pre-trained model on noisy label data. To this end, we rather exploit the overfitting property of a trained model to identify mislabeled samples. Specifically, our post-training approach gradually removes samples with high influence on the decision boundary and refines the decision boundary to improve generalization performance. Our post-training approach creates great synergies when combined with the existing LNL methods. Experimental results on various real-world and synthetic benchmark datasets demonstrate the validity of our approach in diverse realistic scenarios.

翻译：深度神经网络因其高容量特性，即便面对噪声标签也极易产生过拟合，从而导致模型泛化性能下降。为解决这一问题，我们提出了一种基于后训练学习噪声标签（LNL）的新方法，该方法能显著提升任意预训练模型在噪声标签数据上的泛化性能。为此，我们转而利用已训练模型的过拟合特性来识别误标注样本。具体而言，我们的后训练方法逐步移除对决策边界具有高影响力的样本，并通过优化决策边界来提升泛化性能。该方法与现有LNL方法结合时能产生显著的协同效应。在多种真实场景与合成基准数据集上的实验结果表明，我们的方法在各类现实场景中均具有有效性。