3 papers
cs.CV2026
DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
Emre Kavak, Tom Nuno Wolf, Christian Wachinger
Dataset bias often leads deep learning models to exploit spurious correlations instead of task-relevant signals. We introduce the Standard Anti-Causal Model (SAM), a unifying causa…
cs.CV2025
SIC: Similarity-Based Interpretable Image Classification with Neural Networks
Tom Nuno Wolf, Emre Kavak, Fabian Bongratz +1
The deployment of deep learning models in critical domains necessitates a balance between high accuracy and interpretability. We introduce SIC, an inherently interpretable neural n…
cs.GR2025
X-SiT: Inherently Interpretable Surface Vision Transformers for Dementia Diagnosis
Fabian Bongratz, Tom Nuno Wolf, Jaume Gual Ramon +1
Interpretable models are crucial for supporting clinical decision-making, driving advances in their development and application for medical images. However, the nature of 3D volume…