Sharing Generative Models Instead of Private Data: A Simulation Study on Mammography Patch Classification

1 code implementation • 8 Mar 2022 • Zuzanna Szafranowska, Richard Osuala, Bennet Breier, Kaisar Kushibar, Karim Lekadir, Oliver Diaz

Our experiments demonstrate that shared GANs notably increase the performance of both transformer and convolutional classification models and highlight this approach as a viable alternative to inter-centre data sharing.

Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout Classification

1 code implementation • ICLR 2020 • Bennet Breier, Arno Onken

After correction, our best CNN beats the SVM by 6. 12%, achieving a classification accuracy of 96. 32%.

General Classification