Search Results for author:
Found 3 papers, 1 papers with code
XPose: eXplainable Human Pose Estimation
In this paper, we propose XPose, a novel framework that incorporates Explainable AI (XAI) principles into pose estimation.
Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network
Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs.
Resisting Out-of-Distribution Data Problem in Perturbation of XAI
Besides, our solution also resolves a fundamental problem with the faithfulness indicator, a commonly used evaluation metric of XAI algorithms that appears to be sensitive to the OoD issue.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
