A thesis compiled from the author's published works reports that activation maximization cannot interpret medical image classifiers, while prototype-based and feature-co-occurrence methods improve explainable and robust medical classification.
An interpretable unsupervised bayesian network model for fault detection and diagnosis.Control Engineering Practice, 127:105304, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Human-aligned Deep Learning: Explainability, Causality, and Biological Inspiration
A thesis compiled from the author's published works reports that activation maximization cannot interpret medical image classifiers, while prototype-based and feature-co-occurrence methods improve explainable and robust medical classification.