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.
|Title of host publication||36th International Conference on Machine Learning, ICML 2019|
|Publisher||International Machine Learning Society (IMLS)|
|Number of pages||10|
|Publication status||Published - 2019|
|Event||36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States|
Duration: 2019 Jun 9 → 2019 Jun 15
|Name||36th International Conference on Machine Learning, ICML 2019|
|Conference||36th International Conference on Machine Learning, ICML 2019|
|Period||19/6/9 → 19/6/15|
Bibliographical notePublisher Copyright:
© 36th International Conference on Machine Learning, ICML 2019. All rights reserved.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Human-Computer Interaction