DConAD is a differencing-based contrastive transformer framework that scores anomalies by the KL divergence between two learned views, claiming state-of-the-art F1 on five time series benchmarks.
Anomaly detection in uasn localization based on time series analysis and fuzzy logic,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection
DConAD is a differencing-based contrastive transformer framework that scores anomalies by the KL divergence between two learned views, claiming state-of-the-art F1 on five time series benchmarks.