Pixel-level saliency maps outperform point-specific maps for explaining writer identification and verification networks, though the forensic-support claim rests on a limited qualitative evaluation.
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
-
Transparency Techniques for Neural Networks trained on Writer Identification and Writer Verification
Pixel-level saliency maps outperform point-specific maps for explaining writer identification and verification networks, though the forensic-support claim rests on a limited qualitative evaluation.