Concept vectors in an autoencoder's latent space produce stable counterfactual explanations for large chest X-ray pathologies, but the method does not beat the Latent Shift baseline.
Diffusion visual counterfactual explanations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays
Concept vectors in an autoencoder's latent space produce stable counterfactual explanations for large chest X-ray pathologies, but the method does not beat the Latent Shift baseline.