Model Vulnerability to Distributional Shifts over Image Transformation Sets

By Riccardo Volpi, Vittorio Murino. 2019

27 citations recorded by the source corpus.

We are concerned with the vulnerability of computer vision models to distributional shifts. We cast this problem in terms of combinatorial optimization, evaluating the regions in the input space where a (black-box) model is more vulnerable. This is carried out by combining image transformations from a given set and standard search algorithms. We embed this idea in a training procedure, where we define new data augmentation rules over iterations, accordingly to the image transformations that the current model is most vulnerable to. An empirical evaluation on classification and semantic segmentation problems suggests that the devised algorithm allows to train models more robust against content-preserving image transformations, and in general, against distributional shifts.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Kazuki Yoshizoe
2. Hideki Nakayama
3. Ryuichiro Hataya
4. Jan Zdenek

Citations in the corpus

• Faster AutoAugment: Learning Augmentation Strategies using Backpropagation (2019, methodology): “One direction is to search for better combinations of symbolic operations using black-box optimization techniques such as reinforcement learning [5,24], evolution strategy [32], Bayesian optimization [18] and population-based training [12].”