EPIC fits an invertible channel-disentangling transform on top of a frozen pretrained classifier to produce prototype-based explanations while exactly preserving the original predictions.
B-cos networks: Alignment is all we need for interpretability
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
EPIC: Explanation of Pretrained Image Classification Networks via Prototype
EPIC fits an invertible channel-disentangling transform on top of a frozen pretrained classifier to produce prototype-based explanations while exactly preserving the original predictions.