Song Hwanjun, Kim Minseok, Park Dongmin, Shin Yooju, Lee Jae-Gil
IEEE Trans Neural Netw Learn Syst. 2023 Nov;34(11):8135-8153. doi: 10.1109/TNNLS.2022.3152527. Epub 2023 Oct 27.
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.
在大量大数据的帮助下，深度学习在众多领域取得了显著成功。然而，由于在许多实际场景中缺乏高质量标签，数据标签的质量成为一个问题。由于噪声标签会严重降低深度神经网络的泛化性能，从噪声标签中学习（稳健训练）正成为现代深度学习应用中的一项重要任务。在本次综述中，我们首先从监督学习的角度描述带标签噪声学习的问题。接下来，我们对62种先进的稳健训练方法进行了全面综述，所有这些方法根据其方法差异分为五组，随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，包括公开的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，可为未来的研究提供指导。
