Stylized Synthetic Augmentation further improves Corruption Robustness

• URL: http://arxiv.org/abs/2512.15675v3
• Date: Fri, 19 Dec 2025 10:55:54 GMT
• Title: Stylized Synthetic Augmentation further improves Corruption Robustness
• Authors: Georg Siedel, Rojan Regmi, Abhirami Anand, Weijia Shao, Silvia Vock, Andrey Morozov,
• Abstract summary: This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer.<n>We show that although applying style transfer on synthetic images degrades their quality with respect to the common Frechet Inception Distance metric, these images are surprisingly beneficial for model training.
• Score: 4.206961078715932
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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

Related papers

• Stylized Structural Patterns for Improved Neural Network Pre-training [1.8641315013048299]
  Deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns.<n>Recent works suggest synthetic data as an alternative, yet models trained with it often underperform.<n>We propose an improved neural fractal formulation through which we introduce a new class of synthetic data.<n>Second, we propose reverse stylization, a technique that transfers visual features from a small, license-free set of real images onto synthetic datasets.
  arXiv  Detail & Related papers  (2025-06-24T09:47:31Z)
• CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI [58.35348718345307]
  Current efforts to distinguish between real and AI-generated images may lack generalization.<n>We propose a novel framework, Co-Spy, that first enhances existing semantic features.<n>We also create Co-Spy-Bench, a comprehensive dataset comprising 5 real image datasets and 22 state-of-the-art generative models.
  arXiv  Detail & Related papers  (2025-03-24T01:59:29Z)
• LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning [1.786053901581251]
  Deep learning models often struggle to maintain consistent performance when confronted with Out-of-Distribution (OOD) samples.<n>We introduce LayerMix, an innovative data augmentation approach that systematically enhances model robustness.<n>Our method generates semantically consistent synthetic samples that significantly improve neural network generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-08T22:22:44Z)
• Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion [13.196774986841469]
  We show that by focusing on modeling visual perception rather than the data distribution, we can achieve a good trade-off between visual quality and bit rate.<n>We do this by optimizing C3, an overfitted image, for Wasserstein Distortion (WD)
  arXiv  Detail & Related papers  (2024-11-30T15:05:01Z)
• FairDiff: Fair Segmentation with Point-Image Diffusion [15.490776421216689]
  Our research adopts a data-driven strategy-enhancing data balance by integrating synthetic images. We formulate the problem in a joint optimization manner, in which three networks are optimized towards the goal of empirical risk and fairness. Our model achieves superior fairness segmentation performance compared to the state-of-the-art fairness learning models.
  arXiv  Detail & Related papers  (2024-07-08T17:59:58Z)
• Robust Classification by Coupling Data Mollification with Label Smoothing [25.66357344079206]
  We propose a novel approach of coupling data mollification, in the form of image noising and blurring, with label smoothing to align predicted label confidences with image degradation.<n>We demonstrate improved robustness and uncertainty on the corrupted image benchmarks of CIFAR, TinyImageNet and ImageNet datasets.
  arXiv  Detail & Related papers  (2024-06-03T16:21:29Z)
• Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
  We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability. We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images. Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
  arXiv  Detail & Related papers  (2024-03-28T22:25:05Z)
• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• Scaling Laws of Synthetic Images for Model Training ... for Now [54.43596959598466]
  We study the scaling laws of synthetic images generated by state of the art text-to-image models. We observe that synthetic images demonstrate a scaling trend similar to, but slightly less effective than, real images in CLIP training.
  arXiv  Detail & Related papers  (2023-12-07T18:59:59Z)
• Robustness-Guided Image Synthesis for Data-Free Quantization [15.91924736452861]
  We propose Robustness-Guided Image Synthesis (RIS) to enrich the semantics of synthetic images and improve image diversity. RIS is a simple but effective method to enrich the semantics of synthetic images and improve image diversity. We achieve state-of-the-art performance for various settings on data-free quantization and can be extended to other data-free compression tasks.
  arXiv  Detail & Related papers  (2023-10-05T16:39:14Z)
• Exploring the Robustness of Human Parsers Towards Common Corruptions [99.89886010550836]
  We construct three corruption robustness benchmarks, termed LIP-C, ATR-C, and Pascal-Person-Part-C, to assist us in evaluating the risk tolerance of human parsing models. Inspired by the data augmentation strategy, we propose a novel heterogeneous augmentation-enhanced mechanism to bolster robustness under commonly corrupted conditions.
  arXiv  Detail & Related papers  (2023-09-02T13:32:14Z)
• Improving robustness against common corruptions with frequency biased models [112.65717928060195]
  unseen image corruptions can cause a surprisingly large drop in performance. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation. We propose a new regularization scheme that minimizes the total variation (TV) of convolution feature-maps to increase high-frequency robustness.
  arXiv  Detail & Related papers  (2021-03-30T10:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.