The paper learns sparse masks over a DCNN's top-layer filters that preserve the inferred class (contrastive) or flip it to an alter class (counterfactual), evaluated on CUB bird classification.
Title resolution pending
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
-
Towards Counterfactual and Contrastive Explainability and Transparency of DCNN Image Classifiers
The paper learns sparse masks over a DCNN's top-layer filters that preserve the inferred class (contrastive) or flip it to an alter class (counterfactual), evaluated on CUB bird classification.