AIConfPaper
← Search

Stefan Kolek

5 accepted papers

2025

Learning Interpretable Queries for Explainable Image Classification with Information Pursuit

Stefan Kolek, Aditya Chattopadhyay, Kwan Ho Ryan Chan, Hector Andrade-Loarca, Gitta Kutyniok, René Vidal
ICCV 2025poster

Information Pursuit (IP) is a recently introduced learning framework to construct classifiers that are interpretable-by-design. Given a set of task-relevant and interpretable data queries, IP selects a small subset of the most informative queries and makes predictions based on the gathered query-ans…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Beyond the Calibration Point: Mechanism Comparison in Differential Privacy

Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert
ICML 2024poster

In differentially private (DP) machine learning, the privacy guarantees of DP mechanisms are often reported and compared on the basis of a single $(\varepsilon, \delta)$-pair. This practice overlooks that DP guarantees can vary substantially even between mechanisms sharing a given $(\varepsilon, \de…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

Explaining Image Classifiers With Multiscale Directional Image Representation

Stefan Kolek, Robert Windesheim, Hector Andrade-Loarca, Gitta Kutyniok, Ron Levie
CVPR 2023poster

Image classifiers are known to be difficult to interpret and therefore require explanation methods to understand their decisions. We present ShearletX, a novel mask explanation method for image classifiers based on the shearlet transform -- a multiscale directional image representation. Current mask…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2023

Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning

Georgios Kaissis, Alexander Ziller, Stefan Kolek, Anneliese Riess, Daniel Rueckert
NeurIPS 2023poster

Differentially private mechanisms restrict the membership inference capabilities of powerful (optimal) adversaries against machine learning models. Such adversaries are rarely encountered in practice. In this work, we examine a more realistic threat model relaxation, where (sub-optimal) adversaries…

Cited by 6Source ↗PDF ↗Scholar ↗
2022

Cartoon Explanations of Image Classifiers

Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok
ECCV 2022poster

"We present CartoonX (Cartoon Explanation), a novel model-agnostic explanation method tailored towards image classifiers and based on the rate-distortion explanation (RDE) framework. Natural images are roughly piece-wise smooth signals---also called cartoon-like images---and tend to be sparse in the…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗