no code implementations • 16 Jun 2021 • Hyeoncheol Cho, Youngrock Oh, Eunjoo Jeon
SEEN provides a simple but effective method to enhance the explanation quality of GNN model outputs, and this method is applicable in combination with most explainability techniques.
1 code implementation • ICCV 2021 • Hyungsik Jung, Youngrock Oh
In this paper, we revisit the intrinsic linearity of CAM with respect to the activation maps; we construct an explanation model of CNN as a linear function of binary variables that denote the existence of the corresponding activation maps.