4 citations · 9 across the 10 of their papers we have counts for
4 papers · 1 filter
How to Manipulate CNNs to Make Them Lie: the GradCAM Case
Tom Viering, Ziqi Wang, Marco Loog +1
Recently many methods have been introduced to explain CNN decisions. However, it has been shown that some methods can be sensitive to manipulation of the input. We continue this li…
Learning an MR acquisition-invariant representation using Siamese neural networks
Wouter M. Kouw, Marco Loog, Wilbert Bartels +1
Generalization of voxelwise classifiers is hampered by differences between MRI-scanners, e.g. different acquisition protocols and field strengths. To address this limitation, we pr…
Object-Extent Pooling for Weakly Supervised Single-Shot Localization
Amogh Gudi, Nicolai van Rosmalen, Marco Loog +1
In the face of scarcity in detailed training annotations, the ability to perform object localization tasks in real-time with weak-supervision is very valuable. However, the computa…
Scale-Regularized Filter Learning
Marco Loog, François Lauze
We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature…