Proceedings

Learning Interpretable Concept Groups in CNNs

Saurabh Varshneya, Antoine Ledent, Robert A. Vandermeulen, Yunwen Lei, Matthias Enders, Damian Borth, Marius Kloft

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1061-1067.

https://doi.org/10.24963/ijcai.2021/147

Keywords

  • Computer Vision: 2D and 3D Computer Vision
  • Machine Learning: Deep Learning
  • Machine Learning: Explainable/Interpretable Machine Learning

Abstract

We propose a novel training methodology---Concept Group Learning (CGL)---that encourages training of interpretable CNN filters by partitioning filters in each layer into \emph{concept groups}, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy that forces filters in the same group to be active in similar image regions for a given layer. We additionally use a regularizer to encourage a sparse weighting of the concept groups in each layer so that a few concept groups can have greater importance than others. We quantitatively evaluate CGL's model interpretability using standard interpretability evaluation techniques and find that our method increases interpretability scores in most cases. Qualitatively we compare the image regions which are most active under filters learned using CGL versus filters learned without CGL and find that CGL activation regions more strongly concentrate around semantically relevant features.

Saurabh Varshneya, Antoine Ledent, Robert A. Vandermeulen, Yunwen Lei, Matthias Enders, Damian Borth, and Marius Kloft. 2021. Learning Interpretable Concept Groups in CNNs. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1061–1067. https://doi.org/10.24963/ijcai.2021/147
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards