Stylized Synthetic Augmentation further improves Corruption Robustness
This addresses the problem of corruption robustness for image classifiers, representing an incremental improvement by combining existing techniques.
The paper tackles the vulnerability of deep vision models to common corruptions by proposing a training data augmentation pipeline that combines synthetic image data with neural style transfer, achieving state-of-the-art corruption robustness with 93.54%, 74.9%, and 50.86% robust accuracy on CIFAR-10-C, CIFAR-100-C, and TinyImageNet-C benchmarks, respectively.
This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of deep vision models to common corruptions. We show that although applying style transfer on synthetic images degrades their quality with respect to the common Frechet Inception Distance (FID) metric, these images are surprisingly beneficial for model training. We conduct a systematic empirical analysis of the effects of both augmentations and their key hyperparameters on the performance of image classifiers. Our results demonstrate that stylization and synthetic data complement each other well and can be combined with popular rule-based data augmentation techniques such as TrivialAugment, while not working with others. Our method achieves state-of-the-art corruption robustness on several small-scale image classification benchmarks, reaching 93.54%, 74.9% and 50.86% robust accuracy on CIFAR-10-C, CIFAR-100-C and TinyImageNet-C, respectively