Robust inference via generative classifiers for handling noisy labels

Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, Jinwoo Shin

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

13 Citations (Scopus)


Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a novel inference method, termed Robust Generative classifier (RoG), applicable to any discriminative (e.g., softmax) neural classifier pre-trained on noisy datasets. In particular, we induce a generative classifier on top of hidden feature spaces of the pre-trained DNNs, for obtaining a more robust decision boundary. By estimating the parameters of generative classifier using the minimum co-variance determinant estimator, we significantly improve the classification accuracy with neither re-training of the deep model nor changing its architectures. With the assumption of Gaussian distribution for features, we prove that RoG generalizes better than baselines under noisy labels. Finally, we propose the ensemble version of RoG to improve its performance by investigating the layer-wise characteristics of DNNs. Our extensive experimental results demonstrate the superiority of RoG given different learning models optimized by several training techniques to handle diverse scenarios of noisy labels.

Original languageEnglish
Title of host publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)
Number of pages10
ISBN (Electronic)9781510886988
Publication statusPublished - 2019
Event36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States
Duration: 2019 Jun 92019 Jun 15

Publication series

Name36th International Conference on Machine Learning, ICML 2019


Conference36th International Conference on Machine Learning, ICML 2019
Country/TerritoryUnited States
CityLong Beach

Bibliographical note

Funding Information:
This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No.2017-0-01779, A machine learning and statistical inference framework for explainable artificial intelligence), NSF CAREER IIS-1453651, Sloan Research Fellowship, and Kwanjcong Educational Foundation Scholarship. This work is partially supported by DARPA under Grant 00009970, Wechat. We also thank Dawn Song, Dan Hendrycks, Sungsoo Ahn and Insu Han for helpful discussions.

Publisher Copyright:
© 36th International Conference on Machine Learning, ICML 2019. All rights reserved.

All Science Journal Classification (ASJC) codes

  • Education
  • Computer Science Applications
  • Human-Computer Interaction


Dive into the research topics of 'Robust inference via generative classifiers for handling noisy labels'. Together they form a unique fingerprint.

Cite this