Now showing items 1-2 of 2
Controllably Sparse Perturbations of Robust Classifiers for Explaining Predictions and Probing Learned Concepts
(The Eurographics Association, 2021)
Explaining the predictions of a deep neural network (DNN) in image classification is an active area of research. Many methods focus on localizing pixels, or groups of pixels, which maximize a relevance metric for the ...
ModelSpeX: Model Specification Using Explainable Artificial Intelligence Methods
(The Eurographics Association, 2020)
Explainable artificial intelligence (XAI) methods aim to reveal the non-transparent decision-making mechanisms of black-box models. The evaluation of insight generated by such XAI methods remains challenging as the applied ...