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.
Epvt: Environment-aware prompt vision transformer for domain generalization in skin lesion recognition
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.