m-pax_lib

This repository contains a framework which allows for enhanced model interpretability and model robustness. The framework utilizes interpretable disentangled representations for downstream-task prediction which are in a second step visualized and evaluated through a multipath-attribution mapping.

Visualizing and interpreting disentangled representations through multipath-attribution maps. © Lukas Klein

Find m-pax_lib on Helmholtz Imaging Connect
Authors: Lukas Klein, João B. S. Carvalho