Norman Mu
Research Subjects
Norman Mu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Balaji Lakshminarayanan
Google research
1 shared publication - Barret Zoph
Google research
1 shared publication - Dan Hendrycks
University of California Berkeley
1 shared publication - Ekin Dogus Cubuk
Google DeepMind, London, UK
1 shared publication - Justin Gilmer
Google Research Brain Team
1 shared publication
Latest Publications
- Open Access
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated in practice. When the train and test distributions are mismatched, accuracy can plummet. Currently there are few techniques that improve robustness to unforeseen data shifts encountered during deployment. In this work, we propose a technique to improve the robustness and uncertainty estimates of image classifiers. We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions. AugMix significantly improves robustness and uncertainty measures on challenging image classification benchmarks, closing the gap between previous methods and the best possible performance in some cases by more than half.
Open AccessAugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated in practice. When the train and test distributions are mismatched, accuracy can plummet. Currently there are few techniques that improve robustness to unforeseen data shifts encountered during deployment. In this work, we propose a technique to improve the robustness and uncertainty estimates of image classifiers. We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions. AugMix significantly improves robustness and uncertainty measures on challenging image classification benchmarks, closing the gap between previous methods and the best possible performance in some cases by more than half.