Grad Centroid Activation Mapping for Convolutional Neural Networks

Baptiste Lafabregue (1, 2) , Jonathan Weber (1) , Pierre Gançarski (2) , Germain Forestier (1)

1 IRIMAS - Institut de Recherche en Informatique Mathématiques Automatique Signal - IRIMAS - UR 7499
2 ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie

An important research effort has been recently dedicated to understand the decision mechanism of deep neural networks. Among them, Class Activation Mapping (CAM) and its variations have proved their capacity to obtain useful insights about Convolutional Neural Network (CNN) models' decisions. However, these methods remain limited to the supervised case regardless of CNN-based advances in unsupervised tasks such as clustering. To fill this gap, we propose a new method called Grad-CeAM for centroid-based clustering methods used on CNN representation. Through an experimental study, we show that our method has the capacity to localize discriminating features used by a CNN model to create its representation and that it can be used to explain the clusters assignment. We also show that this method can be used in different application domains by providing uses cases on time series and images clustering.

Mots clés: Activation Map; Clustering; Deep Learning; Interpretability; Time series; Image

Domaines: Intelligence artificielle [cs.AI]

Baptiste Lafabregue, Jonathan Weber, Pierre Gançarski, Germain Forestier. Grad Centroid Activation Mapping for Convolutional Neural Networks. IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Nov 2021, Washington (virtual), United States. ⟨10.1109/ICTAI52525.2021.00033⟩. ⟨hal-03451019⟩