Human-Centered Explanations: Lessons Learned from Image Classification for Medical and Clinical Decision Making

B Finzel - KI-Künstliche Intelligenz, 2024 - Springer
To date, there is no universal explanatory method for making decisions of an AI-based
system transparent to human decision makers. This is because, depending on the …

When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX

B Finzel, P Hilme, J Rabold, U Schmid - arXiv preprint arXiv:2405.01661, 2024 - arxiv.org
Explanations for Convolutional Neural Networks (CNNs) based on relevance of input pixels
might be too unspecific to evaluate which and how input features impact model decisions …

Near Hit and Near Miss Example Explanations for Model Revision in Binary Image Classification

B Finzel, J Knoblach, A Thaler, U Schmid - International Conference on …, 2024 - Springer
Abstract Model revision is a challenging task in image classification. It is usually performed
to correct the predictions of misclassified examples. Support examples, which are similar to …