no code implementations • 13 Mar 2024 • Lorenz Linhardt, Marco Morik, Sidney Bender, Naima Elosegui Borras
Diffusion models, trained on large amounts of data, showed remarkable performance for image synthesis.
no code implementations • 2 Oct 2023 • Sidney Bender, Christopher J. Anders, Pattarawatt Chormai, Heike Marxfeld, Jan Herrmann, Grégoire Montavon
This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of human expert feedback.
no code implementations • 2 Oct 2021 • Sidney Bender, Tim Joseph, Marius Zoellner
Our experiments using different modalities in the CARLA simulator showed that this enables CCWM to outperform state-of-the-art domain adaptation approaches.