The framework learns damage-sensitive but variability-invariant representations from vibration signals via self-supervised autoencoding with VICReg regularization and frequency constraints.
Transferring self-supervised pretrained models for shm data anomaly detection with scarce labeled data.Structural Control and Health Monitoring2025; 2025(1): 2414195
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
-
Disentangling Damage from Operational Variability: A Label-Free Self-Supervised Representation Learning Framework for Output-Only Structural Damage Identification
The framework learns damage-sensitive but variability-invariant representations from vibration signals via self-supervised autoencoding with VICReg regularization and frequency constraints.