Implicit neural networks can generate attribution masks that are smoother under area constraints and iteratively yield multiple non-overlapping explanations for a deep model's prediction.
Real time image saliency for black box classifiers
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Generating visual explanations from deep networks using implicit neural representations
Implicit neural networks can generate attribution masks that are smoother under area constraints and iteratively yield multiple non-overlapping explanations for a deep model's prediction.