On synthetic AND/OR/XOR tasks, saliency methods frequently rank irrelevant baseline inputs above logically relevant ones, and retrained models can recover class information from masked inputs, indicating that score order can encode extra information.
Grad-cam++: Gener- alized gradient-based visual explanations for deep convo- lutional networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretation
On synthetic AND/OR/XOR tasks, saliency methods frequently rank irrelevant baseline inputs above logically relevant ones, and retrained models can recover class information from masked inputs, indicating that score order can encode extra information.