DeepAI AI Chat
Log In Sign Up

Scalable Certified Segmentation via Randomized Smoothing

by   Marc Fischer, et al.

We present a new certification method for image and point cloud segmentation based on randomized smoothing. The method leverages a novel scalable algorithm for prediction and certification that correctly accounts for multiple testing, necessary for ensuring statistical guarantees. The key to our approach is reliance on established multiple-testing correction mechanisms as well as the ability to abstain from classifying single pixels or points while still robustly segmenting the overall input. Our experimental evaluation on synthetic data and challenging datasets, such as Pascal Context, Cityscapes, and ShapeNet, shows that our algorithm can achieve, for the first time, competitive accuracy and certification guarantees on real-world segmentation tasks. We provide an implementation at


page 1

page 19


Robust and Accurate – Compositional Architectures for Randomized Smoothing

Randomized Smoothing (RS) is considered the state-of-the-art approach to...

Hierarchical correction of p-values via a tree running Ornstein-Uhlenbeck process

Statistical testing is classically used as an exploratory tool to search...

Contrastive Boundary Learning for Point Cloud Segmentation

Point cloud segmentation is fundamental in understanding 3D environments...

Localized Randomized Smoothing for Collective Robustness Certification

Models for image segmentation, node classification and many other tasks ...

Intriguing Properties of Input-dependent Randomized Smoothing

Randomized smoothing is currently considered the state-of-the-art method...

Robustness Certification of Visual Perception Models via Camera Motion Smoothing

A vast literature shows that the learning-based visual perception model ...

Smooth-Reduce: Leveraging Patches for Improved Certified Robustness

Randomized smoothing (RS) has been shown to be a fast, scalable techniqu...