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 Clothing1M dataset. (K. Nishi and Y. Ding contributed equally to this work)
翻译:在现实世界的数据集中,隐性标签无处不在。最近一些培训深神经网络的成功方法(DNNS),对于标签噪音而言是有力的,这些成功方法使用了两种主要技术:在热潮阶段根据损失过滤样本,以整理一套初步的清洁标签样本,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。由于这些算法的一些共性,我们发现,使用一套增强的样本对损失模型进行筛选,以及使用另一套用于学习的数据集,对于随后的损失计算最为有效,可以改进最新状态和其他前方法的结果。此外,我们发现,在暖潮期应用增强能对正确与错误标签样本之间的损失趋同行为产生消极影响。我们将这一增强战略引入州-世界数据集Stral1,以及真实的数据集。由于这些算法的一些共性,我们可以提高绝对的精确性,因此,在10-10-K的精确性数据中可以改进我们整个的精确性水平上,在10-10-10-K的精确度上,我们可以改进了。