Corpus ID: 174802797

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

@article{Lopes2019ImprovingRW,
  title={Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation},
  author={Raphael Gontijo Lopes and Dong Yin and Ben Poole and J. Gilmer and E. Cubuk},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.02611}
}
  • Raphael Gontijo Lopes, Dong Yin, +2 authors E. Cubuk
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains challenging. Prior work has argued that there is an inherent trade-off between robustness and accuracy, which is exemplified by standard data augment techniques such as Cutout, which improves clean accuracy but not robustness, and additive Gaussian noise, which… CONTINUE READING
    49 Citations
    RandAugment: Practical data augmentation with no separate search
    • 99
    SmoothMix: a Simple Yet Effective Data Augmentation to Train Robust Classifiers
    • 1
    • PDF
    Does Data Augmentation Benefit from Split BatchNorms
    • Highly Influenced
    • PDF
    Auxiliary Training: Towards Accurate and Robust Models
    • 3
    • PDF
    A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions
    • 21
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 58 REFERENCES
    A Fourier Perspective on Model Robustness in Computer Vision
    • 83
    • PDF
    Improved Regularization of Convolutional Neural Networks with Cutout
    • 863
    • Highly Influential
    • PDF
    Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
    • 60
    • Highly Influential
    Unsupervised Data Augmentation
    • 141
    AutoAugment: Learning Augmentation Policies from Data
    • 537
    • PDF
    Using Pre-Training Can Improve Model Robustness and Uncertainty
    • 133
    • PDF
    Learning Robust Representations by Projecting Superficial Statistics Out
    • 53
    • PDF
    Do CIFAR-10 Classifiers Generalize to CIFAR-10?
    • 141
    • PDF
    Generalisation in humans and deep neural networks
    • 176
    • PDF
    Surprising Effectiveness of Few-Image Unsupervised Feature Learning
    • 10