Training Classifiers that are Universally Robust to All Label Noise Levels

Jingyi Xu, Tony Q.S. Quek, Kai Fong Ernest Chong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


For classification tasks, deep neural networks are prone to overfitting in the presence of label noise. Although existing methods are able to alleviate this problem at low noise levels, they encounter significant performance reduction at high noise levels, or even at medium noise levels when the label noise is asymmetric. To train classifiers that are universally robust to all noise levels, and that are not sensitive to any variation in the noise model, we propose a distillation-based framework that incorporates a new subcategory of Positive-Unlabeled learning. In particular, we shall assume that a small subset of any given noisy dataset is known to have correct labels, which we treat as 'positive', while the remaining noisy subset is treated as 'unlabeled'. Our framework consists of the following two components: (1) We shall generate, via iterative updates, an augmented clean subset with additional reliable 'positive' samples filtered from 'unlabeled' samples; (2) We shall train a teacher model on this larger augmented clean set. With the guidance of the teacher model, we then train a student model on the whole dataset. Experiments were conducted on the CIFAR-10 dataset with synthetic label noise at multiple noise levels for both symmetric and asymmetric noise. The results show that our framework generally outperforms at medium to high noise levels. We also evaluated our framework on Clothing1M, a real-world noisy dataset, and we achieved 2.94% improvement in accuracy over existing state-of-the-art methods.

Original languageEnglish
Title of host publicationIJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9780738133669
Publication statusPublished - 2021 Jul 18
Event2021 International Joint Conference on Neural Networks, IJCNN 2021 - Virtual, Shenzhen, China
Duration: 2021 Jul 182021 Jul 22

Publication series

NameProceedings of the International Joint Conference on Neural Networks


Conference2021 International Joint Conference on Neural Networks, IJCNN 2021
CityVirtual, Shenzhen

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence


Dive into the research topics of 'Training Classifiers that are Universally Robust to All Label Noise Levels'. Together they form a unique fingerprint.

Cite this