论文标题
带有标签噪声的深度学习：一种分层方法
Deep Learning with Label Noise: A Hierarchical Approach
论文作者
论文摘要
深度神经网络容易受到标签噪声的影响。改善鲁棒性的现有方法，例如元学习和正则化，通常需要对网络体系结构进行重大更改或仔细调整优化过程。在这项工作中，我们提出了一种简单的层次结构方法，该方法在训练深度学习模型时结合了标签层次结构。我们的方法不需要更改网络体系结构或优化过程。我们通过广泛的模拟和真实数据集以及各种标签噪声类型研究我们的分层网络。我们的分层方法可以通过标签噪声在学习中的常规深层神经网络上改善。将我们的分层方法与预训练的模型相结合，可以在现实世界嘈杂的数据集中实现最新的性能。
Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization procedure. In this work, we propose a simple hierarchical approach that incorporates a label hierarchy when training the deep learning models. Our approach requires no change of the network architecture or the optimization procedure. We investigate our hierarchical network through a wide range of simulated and real datasets and various label noise types. Our hierarchical approach improves upon regular deep neural networks in learning with label noise. Combining our hierarchical approach with pre-trained models achieves state-of-the-art performance in real-world noisy datasets.
