Deep metric learning with L2-normalized embeddings and prototype-based matching achieves OSCR of 0.9945 and EER of 1.57% on large-scale vein datasets under strict open-set subject-disjoint protocols.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The method detects unknown faults in ultrasonic metal welding at 96% accuracy and incorporates new fault types from only five labeled samples to reach 98% classification accuracy.
citing papers explorer
-
Open-Set Vein Biometric Recognition with Deep Metric Learning
Deep metric learning with L2-normalized embeddings and prototype-based matching achieves OSCR of 0.9945 and EER of 1.57% on large-scale vein datasets under strict open-set subject-disjoint protocols.
-
Adaptive Unknown Fault Detection and Few-Shot Continual Learning for Condition Monitoring in Ultrasonic Metal Welding
The method detects unknown faults in ultrasonic metal welding at 96% accuracy and incorporates new fault types from only five labeled samples to reach 98% classification accuracy.