# Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets

arXiv: https://arxiv.org/abs/1903.11900 · HTML: https://mlsanity.com/paper/1903.11900/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 12 of 12)

- [Semi-Supervised Domain Generalization with Stochastic StyleMatch](https://mlsanity.com/paper/2106.00592/) (2021)
- [Uncertainty-guided Model Generalization to Unseen Domains](https://mlsanity.com/paper/2103.07531/) (2021)
- [Attention Consistency on Visual Corruptions for Single-Source Domain Generalization](https://mlsanity.com/paper/2204.13091/) (2022)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation](https://mlsanity.com/paper/2303.00914/) (2023)
- [MetaSets: Meta-Learning on Point Sets for Generalizable Representations](https://mlsanity.com/paper/2204.07311/) (2022)
- [Modality-Agnostic Debiasing for Single Domain Generalization](https://mlsanity.com/paper/2303.07123/) (2023)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)
- [Hierarchical Variational Auto-Encoding for Unsupervised Domain Generalization](https://mlsanity.com/paper/2101.09436/) (2021)
- [Explainability-aided Domain Generalization for Image Classification](https://mlsanity.com/paper/2104.01742/) (2021)
- [Contrastive Learning for Cross-Domain Open World Recognition](https://mlsanity.com/paper/2203.09257/) (2022)

## Abstract (arXiv)

We are concerned with the vulnerability of computer vision models to distributional shifts. We formulate a combinatorial optimization problem that allows evaluating the regions in the image space where a given model is more vulnerable, in terms of image transformations applied to the input, and face it with standard search algorithms. We further embed this idea in a training procedure, where we define new data augmentation rules according to the image transformations that the current model is most vulnerable to, over iterations. An empirical evaluation on classification and semantic segmentation problems suggests that the devised algorithm allows to train models that are more robust against content-preserving image manipulations and, in general, against distributional shifts.