Search Results for author:
Found 2 papers, 1 papers with code
GANMEX: Class-Targeted One-vs-One Attributions using GAN-based Model Explainability
Our approach effectively selects the baseline as the closest realistic sample belong to the target class, which allows attribution methods to provide true one-vs-one explanations.
GANMEX: One-vs-One Attributions Guided by GAN-based Counterfactual Explanation Baselines
Attribution methods have been shown as promising approaches for identifying key features that led to learned model predictions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
