SATs aggregate local saliency maps over semantic segments to produce semi-global rankings of feature influence, exposing shortcut reliance even when out-of-distribution accuracy barely changes.
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
-
Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification
SATs aggregate local saliency maps over semantic segments to produce semi-global rankings of feature influence, exposing shortcut reliance even when out-of-distribution accuracy barely changes.