Search Results for author: Christina M. Funke

Found 3 papers, 1 papers with code

Disentanglement and Generalization Under Correlation Shifts

no code implementations29 Dec 2021 Christina M. Funke, Paul Vicol, Kuan-Chieh Wang, Matthias Kümmerer, Richard Zemel, Matthias Bethge

Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e. g., they may change between domains, datasets, or applications) and models that exploit them do not generalize when correlations shift.

Attribute Disentanglement

Cannot find the paper you are looking for? You can Submit a new open access paper.