6 papers
Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches
Rick Wilming, Irem Ozseker, Luca Matteo Cornils +4
Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features. However, current approaches…
Explainable AI needs formalization
Stefan Haufe, Rick Wilming, Benedict Clark +4
The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its c…
Feature salience - not task-informativeness - drives machine learning model explanations
Benedict Clark, Marta Oliveira, Rick Wilming +1
Explainable AI (XAI) promises to provide insight into machine learning models' decision processes, where one goal is to identify failures such as shortcut learning. This promise re…
The effect of whitening on explanation performance
Benedict Clark, Stoyan Karastoyanov, Rick Wilming +1
Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a criti…
GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations
Rick Wilming, Artur Dox, Hjalmar Schulz +3
Large pre-trained language models have become a crucial backbone for many downstream tasks in natural language processing (NLP), and while they are trained on a plethora of data co…
Benchmarking the Influence of Pre-training on Explanation Performance in MR Image Classification
Marta Oliveira, Rick Wilming, Benedict Clark +4
Convolutional Neural Networks (CNNs) are frequently and successfully used in medical prediction tasks. They are often used in combination with transfer learning, leading to improve…