Averaging saliency values within super-pixel groups reduces the variance and improves the stability and generalizability of gradient-based interpretation maps.
How good is your ex- planation? algorithmic stability measures to assess the quality of explanations for deep neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Super-pixel-based Approach to the Stable Interpretation of Neural Networks
Averaging saliency values within super-pixel groups reduces the variance and improves the stability and generalizability of gradient-based interpretation maps.