6 citations · 6 across the 1 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations
Siddhartha Gairola, Moritz Böhle, Francesco Locatello +1
Post-hoc importance attribution methods are a popular tool for "explaining" Deep Neural Networks (DNNs) and are inherently based on the assumption that the explanations can be appl…
cs.CV2022★ 6 cited
B-cos Networks: Alignment is All We Need for Interpretability
Moritz Böhle, Mario Fritz, Bernt Schiele
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace t…