# Achieving Generalizable Robustness of Deep Neural Networks by Stability Training

arXiv: https://arxiv.org/abs/1906.00735 · HTML: https://mlsanity.com/paper/1906.00735/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 7 of 7)

- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [On the effectiveness of adversarial training against common corruptions](https://mlsanity.com/paper/2103.02325/) (2021)
- [Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs](https://mlsanity.com/paper/2110.10645/) (2021)
- [Benchmarking Image Perturbations for Testing Automated Driving Assistance Systems](https://mlsanity.com/paper/2501.12269/) (2025)
- [Improving Robustness for Pose Estimation via Stable Heatmap Regression](https://mlsanity.com/paper/2105.03569/) (2021)
- [Numerical Stability of DeepGOPlus Inference](https://mlsanity.com/paper/2212.06361/) (2022)
- [Real-World Perturbation Testing of Autonomous Driving Systems](https://mlsanity.com/paper/2607.04953/) (2026)

## Abstract (arXiv)

We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and validate its performance against a number of distortion types and transformations including adversarial examples. In our image classification experiments using ImageNet data stability training performs on a par or even outperforms data augmentation for specific transformations, while consistently offering improved robustness against a broader range of distortion strengths and types unseen during training, a considerably smaller hyperparameter dependence and less potentially negative side effects compared to data augmentation.