An entropy-based sampling explanation method for segmentation, paired with a high-salience removal test, is reported to outperform Grad-CAM, Score-CAM, and Seg-Sobol on WHU building footprint segmentation.
The Moonlight Review , urldate =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Entropy-Centric Explainable AI for Remote Sensing Image Segmentation
An entropy-based sampling explanation method for segmentation, paired with a high-salience removal test, is reported to outperform Grad-CAM, Score-CAM, and Seg-Sobol on WHU building footprint segmentation.