@inproceedings{d3b5797a6b694646a12b123a75a96b0e,
title = "Making deep neural networks robust to label noise: A reweighting loss and data filtration",
abstract = "Deep neural networks (DNNs) have achieved astonishing results on a variety of supervised learning tasks owing to a large scale of expert-labeled datasets. However, as recent researches pointed out, the generalization performance of DNNs deteriorates rapidly when training data contains label noise. To alleviate the problem of easily overfitting to label-corrupted data when training DNNs, this paper proposes a robust loss function by reweighting the standard Cross-Entropy loss. For obtaining more robust DNNs under label noise, we further design a framework to jointly optimize model parameters and filtering noisy data during training. Our methods can be thus viewed as online curriculum learning based on both loss function and training datasets. A great deal of experiments have conducted on CIFAR-10, CIFAR-100 and ImageNet under two types of label noise. The results of our proposed method outperforms other state-of-the-art methods.",
keywords = "Curriculum learning, Data filtration, Deep neural networks, Label noise, Robust loss function",
author = "Zhengwen Zhang and Yan Li and Yunjie Li and Ying Qin",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 4th IEEE International Conference on Signal and Image Processing, ICSIP 2019 ; Conference date: 19-07-2019 Through 21-07-2019",
year = "2019",
month = jul,
doi = "10.1109/SIPROCESS.2019.8868645",
language = "English",
series = "2019 IEEE 4th International Conference on Signal and Image Processing, ICSIP 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "289--293",
booktitle = "2019 IEEE 4th International Conference on Signal and Image Processing, ICSIP 2019",
address = "United States",
}