A confidence-feedback-weighted graph matching network achieves 96.36% F1-score on damage site matching by using matchability confidence to weight edge features and applying geometric consistency and hard-example mining.
Automatic classification of true and false laser-induced damage in large aperture optics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Confidence-feedback-weighted graph matching network: online-offline laser-induced damage site matching under complex interference
A confidence-feedback-weighted graph matching network achieves 96.36% F1-score on damage site matching by using matchability confidence to weight edge features and applying geometric consistency and hard-example mining.