Higher-relevance concept groups yield shorter contrastive explanations, and explanation length is stable under 180-degree rotation but not under 10-degree rotation or Gaussian noise.
In: 2020 IEEE Inter- national Conference On Artificial Intelligence Testing (AITest)
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
-
Toward Simple and Robust Contrastive Explanations for Image Classification by Leveraging Instance Similarity and Concept Relevance
Higher-relevance concept groups yield shorter contrastive explanations, and explanation length is stable under 180-degree rotation but not under 10-degree rotation or Gaussian noise.