no code implementations • 6 Oct 2023 • Marcel Kollovieh, Lukas Gosch, Yan Scholten, Marten Lienen, Stephan Günnemann
In this work, we introduce Score-Based Adversarial Generation (ScoreAG), a novel framework that leverages the advancements in score-based generative models to generate adversarial examples beyond $\ell_p$-norm constraints, so-called unrestricted adversarial examples, overcoming their limitations.
1 code implementation • NeurIPS 2023 • Marcel Kollovieh, Abdul Fatir Ansari, Michael Bohlke-Schneider, Jasper Zschiegner, Hao Wang, Yuyang Wang
Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific forecasting or imputation tasks.
no code implementations • 16 Jun 2022 • Marcel Kollovieh, Matthias Keicher, Stephan Wunderlich, Hendrik Burwinkel, Thomas Wendler, Nassir Navab
To this end, we propose a multi-task method based on U-Net that takes T1-weighted MR images as an input to generate synthetic FDG-PET images and classifies the dementia progression of the patient into cognitive normal (CN), cognitive impairment (MCI), and AD.
no code implementations • 5 Aug 2021 • Jan Kukačka, Anja Zenz, Marcel Kollovieh, Dominik Jüstel, Vasilis Ntziachristos
Fundus photography is the primary method for retinal imaging and essential for diabetic retinopathy prevention.