Imperfect labels are ubiquitous in real-world datasets. Several recent successful methods for training deep neural networks (DNNs) robust to label noise have used two primary techniques: filtering samples based on loss during a warm-up phase to curate an initial set of cleanly labeled samples, and using the output of a network as a pseudo-label for subsequent loss calculations. In this paper, we evaluate different augmentation strategies for algorithms tackling the "learning with noisy labels" problem. We propose and examine multiple augmentation strategies and evaluate them using synthetic datasets based on CIFAR-10 and CIFAR-100, as well as on the real-world dataset Clothing1M. Due to several commonalities in these algorithms, we find that using one set of augmentations for loss modeling tasks and another set for learning is the most effective, improving results on the state-of-the-art and other previous methods. Furthermore, we find that applying augmentation during the warm-up period can negatively impact the loss convergence behavior of correctly versus incorrectly labeled samples. We introduce this augmentation strategy to the state-of-the-art technique and demonstrate that we can improve performance across all evaluated noise levels. In particular, we improve accuracy on the CIFAR-10 benchmark at 90% symmetric noise by more than 15% in absolute accuracy and we also improve performance on the real-world dataset Clothing1M. (* equal contribution)
翻译:在现实世界的数据集中,不完全的标签无处不在。最近一些培训深神经网络的成功方法(DNNS)对标签噪声十分活跃,这些成功方法使用了两种主要技术:在热热潮阶段根据损失过滤样本,以整理第一批清洁标签样本,并将网络输出结果作为假标签,用于随后的损失计算。在本文中,我们评估了处理“用噪音标签学习”问题的算法的不同增强战略。我们提出和审查多重增强战略,并利用基于CIFAR-10和CIFAR-100以及真实世界数据集的合成数据集来评估这些战略。由于这些算法中的一些共同点,我们发现,使用一套增强的样本来筛选一组清洁标签样本,以及使用另一套网络的输出作为假标签,作为今后损失计算损失的计算结果。此外,我们发现,在热潮时期应用增强的算法可能会对正确与错误标签样本的损益趋同行为产生消极影响。我们把这一增强战略引入了真实世界数据集。由于这些算法的一些共同点,因此,我们可以用一套增强的精确度的方法来改进我们10-2010年的精确度数据。