AERO proposes a novel two-stage framework tailored for unsupervised anomaly detection in astronomical observations, effectively addressing variate independence and concurrent noise challenges.
CARLA is a novel two-stage self-supervised contrastive representation learning approach that effectively detects anomalies in time series data by learning discriminative representations that distinguish normal and anomalous patterns.
The Sub-Adjacent Transformer leverages a novel attention mechanism focused on sub-adjacent neighborhoods to enhance the detectability of anomalies in time series data.
Complex deep learning models for time series anomaly detection do not provide significant improvements over simple baselines, highlighting the need for rigorous evaluation and the development of interpretable methods.