A VAE-based domain adaptation framework learns shared event representations from two distinct optical systems and achieves 95.3% and 73.5% cross-system accuracy for SOP monitoring, with large gains over single-system DNN baselines.
Machine learn- ing analysis of polarization signatures for distinguishing harmful from non-harmful fiber events,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Variational Autoencoder Domain Adaptation for Cross-System Generalization in ML-Based SOP Monitoring
A VAE-based domain adaptation framework learns shared event representations from two distinct optical systems and achieves 95.3% and 73.5% cross-system accuracy for SOP monitoring, with large gains over single-system DNN baselines.