Enhanced ProtoPNet delivers the highest faithfulness score of 0.1534 when explaining diffusion-based MRI synthesis compared to other prototype methods.
Interpretable im- age classification with differentiable prototypes assignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis
Enhanced ProtoPNet delivers the highest faithfulness score of 0.1534 when explaining diffusion-based MRI synthesis compared to other prototype methods.