Learning From Noisy Labels With Deep Neural Networks: A Survey
Learning From Noisy Labels With Deep Neural Networks: A Survey
复制标题
用深度神经网络从噪声标签中学习：综述
DOI：
10.1109/tnnls.2022.3152527
复制
发表时间：
2022-03-04
影响因子：
10.4
通讯作者：
Lee, Jae-Gil
中科院分区：
文献类型：
--
作者：
Song, Hwanjun;Kim, Minseok;Lee, Jae-Gil
在大量大数据的帮助下，深度学习在许多领域取得了显著的成功。然而，数据标签的质量是一个问题，因为在许多实际场景中缺乏高质量的标签。由于噪声标签严重降低了深度神经网络的泛化性能，从噪声标签中学习（鲁棒训练）成为现代深度学习应用中的重要任务。在这项调查中，我们首先从监督学习的角度描述了带有标签噪声的学习问题。接下来，我们对62种最先进的鲁棒训练方法进行了全面的回顾，所有这些方法都根据其方法差异分为五组，然后对用于评估其优越性的六个属性进行了系统比较。随后，我们对噪声率估计进行了深入分析，并总结了常用的评估方法，包括公共噪声数据集和评估指标。最后，我们提出了几个有前景的研究方向，可以作为未来研究的指导。
Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications. In this survey, we first describe the problem of learning with label noise from a supervised learning perspective. Next, we provide a comprehensive review of 62 state-of-the-art robust training methods, all of which are categorized into five groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority. Subsequently, we perform an in-depth analysis of noise rate estimation and summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics. Finally, we present several promising research directions that can serve as a guideline for future studies.