# Stylized Synthetic Augmentation further improves Corruption Robustness

Source: [Stylized Synthetic Augmentation further improves Corruption Robustness](<https://www.sota2.com/research/paper/69438aa5423ea422657295ea>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-23T05:00:04.997Z

Authors: Georg Siedel, Rojan Regmi, Abhirami Anand, Weijia Shao, Silvia Vock, Andrey Morozov

Published: 2025-12-17T18:28:04.000Z

## Abstract

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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on TinyImageNet (test) (Corruption Metrics)](<https://www.sota2.com/research/sota/image-classification-on-tinyimagenet-test-corruption-metrics.md>): Image Classification; TinyImageNet (test); Accuracy: 74.69.

- [Image Classification on CIFAR-10 (test) (C15/Corruption Metrics)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-c15-corruption-metrics.md>): Image Classification; CIFAR-10 (test); Accuracy: 97.01.

- [Image Classification on CIFAR-100 (test) (Accuracy and Mean Corruption Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-accuracy-and-mean-corruption-accuracy.md>): Image Classification; CIFAR-100 (test); Accuracy: 0.8312.

- [Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy: 96.66.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.15675>)

[PDF](<https://arxiv.org/pdf/2512.15675.pdf>)