FreRA learns to preserve semantically important frequency components and distort the rest, improving contrastive learning for time series classification.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
FreRA learns to preserve semantically important frequency components and distort the rest, improving contrastive learning for time series classification.