129 citations · 131 across the 2 of their papers we have counts for
3 papers
HyperSORT: Self-Organising Robust Training with hyper-networks
Samuel Joutard, Marijn Stollenga, Marc Balle Sanchez +2
Medical imaging datasets often contain heterogeneous biases ranging from erroneous labels to inconsistent labeling styles. Such biases can negatively impact deep segmentation netwo…
Robust vertebra identification using simultaneous node and edge predicting Graph Neural Networks
Vincent Bürgin, Raphael Prevost, Marijn F. Stollenga
Automatic vertebra localization and identification in CT scans is important for numerous clinical applications. Much progress has been made on this topic, but it mostly targets pos…
Deep Networks with Internal Selective Attention through Feedback Connections
Marijn Stollenga, Jonathan Masci, Faustino Gomez +1
Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers.…