no code implementations • ECCV 2020 • Christian Reimers, Jakob Runge, Joachim Denzler
Deep neural networks are tremendously successful in many applications, but end-to-end trained networks often result in hard to understand black-box classifiers or predictors.
no code implementations • 8 Jan 2024 • Christian Reimers, David Hafezi Rachti, Guahua Liu, Alexander J. Winkler
Phenological dates, such as the start and end of the growing season, are critical for understanding the exchange of carbon and water between the biosphere and the atmosphere.
1 code implementation • 26 Jul 2023 • David Friede, Christian Reimers, Heiner Stuckenschmidt, Mathias Niepert
Recent successes in image generation, model-based reinforcement learning, and text-to-image generation have demonstrated the empirical advantages of discrete latent representations, although the reasons behind their benefits remain unclear.
no code implementations • 10 Mar 2021 • Christian Reimers, Paul Bodesheim, Jakob Runge, Joachim Denzler
Often, the bias of a classifier is a direct consequence of a bias in the training dataset, frequently caused by the co-occurrence of relevant features and irrelevant ones.