TrustNet：从可信数据中学习对抗（A）对称标签噪声
TrustNet: Learning from Trusted Data Against (A)symmetric Label Noise
摘要：
对标签噪声的鲁棒性是在大规模数据集上训练的弱监督分类器的关键属性。对标签噪声的鲁棒性是在大规模数据集上训练的弱监督分类器的关键属性。在本文中，我们首先推导出解析界的任何给定的噪声模式。基于这些见解，我们设计了TrustNet，它首先从一小部分可信数据中反向学习噪声损坏的模式，无论是对称的还是非对称的。然后，通过鲁棒的损失函数训练TrustNet，该函数将给定的标签与从学习的噪声模式推断的标签进行加权。权重基于训练时期的模型不确定性进行调整。我们对CIFAR-10和CIFAR-100的合成标签噪声以及具有标签噪声的真实世界数据（即，服装1 M.我们与最先进的方法进行比较，证明了TrustNet在各种噪声模式下的强大鲁棒性。
英文摘要：
Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. In this paper, we first derive analytical bound for any given noise patterns. Based on the insights, we design TrustNet that first adversely learns the pattern of noise corruption, being it both symmetric or asymmetric, from a small set of trusted data. Then, TrustNet is trained via a robust loss function, which weights the given labels against the inferred labels from the learned noise pattern. The weight is adjusted based on model uncertainty across training epochs. We evaluate TrustNet on synthetic label noise for CIFAR-10 and CIFAR-100, and real-world data with label noise, i.e., Clothing1M. We compare against state-of-the-art methods demonstrating the strong robustness of TrustNet under a diverse set of noise patterns.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
