SGLRP initializes layer-wise relevance propagation with the softmax gradient, yielding class-discriminative pixel attribution maps that outperform LRP and CLRP on ImageNet localization metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
SGLRP initializes layer-wise relevance propagation with the softmax gradient, yielding class-discriminative pixel attribution maps that outperform LRP and CLRP on ImageNet localization metrics.