Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs

no code implementations • 24 Jul 2023 • Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard

Existing certified training methods produce models that achieve high provable robustness guarantees at certain perturbation levels.

Universe Points Representation Learning for Partial Multi-Graph Matching

no code implementations • 1 Dec 2022 • Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard

Many challenges from natural world can be formulated as a graph matching problem.

Graph Matching Representation Learning

Efficient and Flexible Sublabel-Accurate Energy Minimization

1 code implementation • 20 Jun 2022 • Zhakshylyk Nurlanov, Daniel Cremers, Florian Bernard

While discrete optimization methods are able to give theoretical optimality guarantees, they can only handle a finite number of labels and therefore suffer from label discretization bias.

Image Denoising