Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?

Deep learning (DL) models are widely used in real-world applications but remain vulnerable to distribution shifts, especially due to weather and lighting changes. Collecting diverse real-world data for testing the robustness of DL models is resource-intensive, making synthetic corruptions an attractive alternative for robustness testing. However, are synthetic corruptions a reliable proxy for real-world corruptions? To answer this, we conduct the largest benchmarking study on semantic segmentation models, comparing performance on real-world corruptions and synthetic corruptions datasets. Our results reveal a strong correlation in mean performance, supporting the use of synthetic corruptions for robustness evaluation. We further analyze corruption-specific correlations, providing key insights to understand when synthetic corruptions succeed in representing real-world corruptions. Open-source Code:this https URL

@article{agnihotri2025_2505.04835,
  title={ Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions? },
  author={ Shashank Agnihotri and David Schader and Nico Sharei and Mehmet Ege Kaçar and Margret Keuper },
  journal={arXiv preprint arXiv:2505.04835},
  year={ 2025 }
}