no code implementations • CVPR 2023 • Ann-Christin Woerl, Jan Disselhoff, Michael Wand
In this paper, we examine gradients of logits of image classification CNNs by input pixel values.
no code implementations • 30 Nov 2022 • Christian H. X. Ali Mehmeti-Göpel, Jan Disselhoff
We perform an empirical study of the behaviour of deep networks when fully linearizing some of its feature channels through a sparsity prior on the overall number of nonlinear units in the network.