ICML 2019oral952 citations

Using Pre-Training Can Improve Model Robustness and Uncertainty

Dan Hendrycks, Kimin Lee, Mantas Mazeika

Abstract

He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional classification metrics, it improves model robustness and uncertainty estimates. Through extensive experiments on label corruption, class imbalance, adversarial examples, out-of-distribution detection, and confidence calibration, we demonstrate large gains from pre-training and complementary effects with task-specific methods. We show approximately a 10% absolute improvement over the previous state-of-the-art in adversarial robustness. In some cases, using pre-training without task-specific methods also surpasses the state-of-the-art, highlighting the need for pre-training when evaluating future methods on robustness and uncertainty tasks.

BibTeX
@InProceedings{pmlr-v97-hendrycks19a,
  title = 	 {Using Pre-Training Can Improve Model Robustness and Uncertainty},
  author =       {Hendrycks, Dan and Lee, Kimin and Mazeika, Mantas},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {2712--2721},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/hendrycks19a/hendrycks19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/hendrycks19a.html},
  abstract = 	 {He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional classification metrics, it improves model robustness and uncertainty estimates. Through extensive experiments on label corruption, class imbalance, adversarial examples, out-of-distribution detection, and confidence calibration, we demonstrate large gains from pre-training and complementary effects with task-specific methods. We show approximately a 10% absolute improvement over the previous state-of-the-art in adversarial robustness. In some cases, using pre-training without task-specific methods also surpasses the state-of-the-art, highlighting the need for pre-training when evaluating future methods on robustness and uncertainty tasks.}
}
Using Pre-Training Can Improve Model Robustness and Uncertainty · ICML 2019