RoseCDL: Robust and Scalable Convolutional Dictionary Learning for Rare-event Detection
This addresses the challenge of rare-event detection in fields like astronomy and biomedical science, offering a practical extension of CDL beyond traditional tasks, though it appears incremental in adapting existing methods.
The paper tackled the problem of detecting rare events in large-scale signals by introducing RoseCDL, a scalable and robust convolutional dictionary learning algorithm, which achieved efficient training and enhanced robustness through stochastic windowing and inline outlier detection.
Identifying recurring patterns and rare events in large-scale signals is a fundamental challenge in fields such as astronomy, physical simulations, and biomedical science. Convolutional Dictionary Learning (CDL) offers a powerful framework for modeling local structures in signals, but its use for detecting rare or anomalous events remains largely unexplored. In particular, CDL faces two key challenges in this setting: high computational cost and sensitivity to artifacts and outliers. In this paper, we introduce RoseCDL, a scalable and robust CDL algorithm designed for unsupervised rare event detection in long signals. RoseCDL combines stochastic windowing for efficient training on large datasets with inline outlier detection to enhance robustness and isolate anomalous patterns. This reframes CDL as a practical tool for event discovery and characterization in real-world signals, extending its role beyond traditional tasks like compression or denoising.