Towards Better Certified Segmentation via Diffusion Models

Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami, Maria Vakalopoulou

Keywords: certified, semantic segmentation, denoising diffusion models, randomized smoothing, robustness

TL;DR: Better certified segmentation leveraging randomized smoothing as well as off-the-shelf denoising diffusion and segmentation models.

Abstract:

The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy. However, like classification models, segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-decision systems like healthcare or autonomous driving.
Recently, randomized smoothing has been proposed to certify segmentation predictions by adding Gaussian noise to the input to obtain theoretical guarantees. Nonetheless, this method exhibits a trade-off between the amount of added noise and the level of certification achieved.
In this paper, we address the problem of certifying segmentation prediction using a combination of randomized smoothing and diffusion models. Our experiments show that combining randomized smoothing and diffusion models significantly improves certified robustness, with results indicating a mean improvement of 21 points in accuracy compared to previous state-of-the-art methods on Pascal-Context and Cityscapes public datasets. Our method is independent of the selected segmentation model and does not need any additional specialized training procedure.
Our pipeline and code will be made publicly available online.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/towards-better-certified-segmentation-via/code)