4 citations · 22 across the 35 of their papers we have counts for
7 papers · 1 filter
Feature Attribution Explanations for Spiking Neural Networks
Elisa Nguyen, Meike Nauta, Gwenn Englebienne +1
Third-generation artificial neural networks, Spiking Neural Networks (SNNs), can be efficiently implemented on hardware. Their implementation on neuromorphic chips opens a broad ra…
Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models
Paul Youssef, Osman Alperen Koraş, Meijie Li +2
Pre-trained Language Models (PLMs) are trained on vast unlabeled data, rich in world knowledge. This fact has sparked the interest of the community in quantifying the amount of fac…
Case-level Breast Cancer Prediction for Real Hospital Settings
Shreyasi Pathak, Jörg Schlötterer, Jeroen Geerdink +4
Breast cancer prediction models for mammography assume that annotations are available for individual images or regions of interest (ROIs), and that there is a fixed number of image…
Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
Phuong Quynh Le, Jörg Schlötterer, Christin Seifert
Models trained with empirical risk minimization (ERM) are known to learn to rely on spurious features, i.e., their prediction is based on undesired auxiliary features which are str…
The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers
Meike Nauta, Christin Seifert
Interpretable part-prototype models are computer vision models that are explainable by design. The models learn prototypical parts and recognise these components in an image, there…
Guidance in Radiology Report Summarization: An Empirical Evaluation and Error Analysis
Jan Trienes, Paul Youssef, Jörg Schlötterer +1
Automatically summarizing radiology reports into a concise impression can reduce the manual burden of clinicians and improve the consistency of reporting. Previous work aimed to en…
Interpreting and Correcting Medical Image Classification with PIP-Net
Meike Nauta, Johannes H. Hegeman, Jeroen Geerdink +3
Part-prototype models are explainable-by-design image classifiers, and a promising alternative to black box AI. This paper explores the applicability and potential of interpretable…