13 citations · 14 across the 4 of their papers we have counts for
4 papers
ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on
Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer +7
Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Before deployment, models should therefore be audited for reliance on concepts such…
Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
Erik Großkopf, Soumya Snigdha Kundu, Hendrik Möller +9
The Panoptic Quality (PQ) metric is the standard for jointly evaluating instance and semantic segmentation. However, its original definition relies on a One-to-One matching between…
Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application
Nys Tjade Siegel, James H. Cole, Mohamad Habes +3
Trustworthy interpretation of deep learning models is critical for neuroimaging applications, yet commonly used Explainable AI (XAI) methods lack rigorous validation, risking misin…
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…