A Shapley-value method with interaction terms that explains object detector decisions by capturing collective pixel contributions for localization and classification.
In con- trast, for Faster R-CNN, patches in specific regions are pref- erentially identified, and the reward value reaches 0.94 after 14 patches are identified
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explaining Object Detectors via Collective Contribution of Pixels
A Shapley-value method with interaction terms that explains object detector decisions by capturing collective pixel contributions for localization and classification.