Max-plus neural networks enable tracing each output to one dominant neuron, allowing a pixel fragility measure that provides more useful explanations than SHAP or Integrated Gradients on medical images.
Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the explainability of max-plus neural networks
Max-plus neural networks enable tracing each output to one dominant neuron, allowing a pixel fragility measure that provides more useful explanations than SHAP or Integrated Gradients on medical images.