no code implementations • 1 Dec 2021 • Maria Wimmer, Gert Sluiter, David Major, Dimitrios Lenis, Astrid Berg, Theresa Neubauer, Katja Bühler
In this work, we propose a pipeline approach, where we first train a set of individual, task-specific models and subsequently investigate the fusion thereof, which is in contrast to the standard model ensembling strategy.
no code implementations • 13 Jul 2020 • Dimitrios Lenis, David Major, Maria Wimmer, Astrid Berg, Gert Sluiter, Katja Bühler
Our solution identifies salient regions of an input image in a single forward-pass by measuring the effect of local image-perturbations on a predictor's score.
no code implementations • 3 Apr 2020 • David Major, Dimitrios Lenis, Maria Wimmer, Gert Sluiter, Astrid Berg, Katja Bühler
Clinical applicability of automated decision support systems depends on a robust, well-understood classification interpretation.