314 citations · 350 across the 8 of their papers we have counts for
4 papers · 1 filter
B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
Moritz Böhle, Navdeeppal Singh, Mario Fritz +1
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…
Studying How to Efficiently and Effectively Guide Models with Explanations
Sukrut Rao, Moritz Böhle, Amin Parchami-Araghi +1
Despite being highly performant, deep neural networks might base their decisions on features that spuriously correlate with the provided labels, thus hurting generalization. To mit…
Better Understanding Differences in Attribution Methods via Systematic Evaluations
Sukrut Rao, Moritz Böhle, Bernt Schiele
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been…
Holistically Explainable Vision Transformers
Moritz Böhle, Mario Fritz, Bernt Schiele
Transformers increasingly dominate the machine learning landscape across many tasks and domains, which increases the importance for understanding their outputs. While their attenti…