Continual Learning for Anomaly Detection in Surveillance Videos
This addresses the challenge of continual learning for anomaly detection in surveillance videos, which is incremental as it builds on existing methods to handle computational and storage issues.
The paper tackled the problem of anomaly detection in surveillance videos by proposing an online method that combines transfer learning and continual learning, resulting in reduced training complexity and avoidance of catastrophic forgetting.
Anomaly detection in surveillance videos has been recently gaining attention. A challenging aspect of high-dimensional applications such as video surveillance is continual learning. While current state-of-the-art deep learning approaches perform well on existing public datasets, they fail to work in a continual learning framework due to computational and storage issues. Furthermore, online decision making is an important but mostly neglected factor in this domain. Motivated by these research gaps, we propose an online anomaly detection method for surveillance videos using transfer learning and continual learning, which in turn significantly reduces the training complexity and provides a mechanism for continually learning from recent data without suffering from catastrophic forgetting. Our proposed algorithm leverages the feature extraction power of neural network-based models for transfer learning, and the continual learning capability of statistical detection methods.