Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

Abstract

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 improves robustness but hurts accuracy. To overcome this trade-off, we introduce Patch Gaussian, a simple augmentation scheme that adds noise to randomly selected patches in an input image. Models trained with Patch Gaussian achieve state of the art on the CIFAR-10 and ImageNetCommon Corruptions benchmarks while also improving accuracy on clean data. We find that this augmentation leads to reduced sensitivity to high frequency noise(similar to Gaussian) while retaining the ability to take advantage of relevant high frequency information in the image (similar to Cutout). Finally, we show that Patch Gaussian can be used in conjunction with other regularization methods and data augmentation policies such as AutoAugment, and improves performance on the COCO object detection benchmark.

References in corpus (8)

• Improved Regularization of Convolutional Neural Networks with Cutout
• Random Erasing Data Augmentation
• Do ImageNet Classifiers Generalize to ImageNet?
• Shake-Shake regularization
• Adversarial Examples Are a Natural Consequence of Test Error in Noise
• Learning Robust Representations by Projecting Superficial Statistics Out
• Analyzing noise in autoencoders and deep networks
• Intriguing Properties of Adversarial Examples

Cited by in corpus (16)

• AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
• Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
• Efficient Certified Defenses Against Patch Attacks on Image Classifiers
• Does enhanced shape bias improve neural network robustness to common corruptions?
• DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
• Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks
• Meta Approach to Data Augmentation Optimization
• Towards Corruption-Agnostic Robust Domain Adaptation
• Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function
• Random Shadows and Highlights: A new data augmentation method for extreme lighting conditions
• RoMA: Robust Model Adaptation for Offline Model-based Optimization
• Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation
• Exploring Frequency Domain Interpretation of Convolutional Neural Networks
• Untapped Potential of Data Augmentation: A Domain Generalization Viewpoint
• Balancing Robustness and Sensitivity using Feature Contrastive Learning
• Robust Face Verification via Disentangled Representations