A robust approach for deep neural networks in presence of label noise: relabelling and filtering instances during training. (arXiv:2109.03748v2 [cs.LG] UPDATED)

Deep learning has outperformed other machine learning algorithms in a variety
of tasks, and as a result, it is widely used. However, like other machine
learning algorithms, deep learning, and convolutional neural networks (CNNs) in
particular, perform worse when the data sets present label noise. Therefore, it
is important to develop algorithms that help the training of deep networks and
their generalization to noise-free test sets. In this paper, we propose a
robust training strategy against label noise, called RAFNI, …

arxiv filtering networks neural networks noise training