Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors

Understand

We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level.

• The novelty of the proposed model is threefold.
• First, we introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects.
• Second, we integrate a teacher decoder and a student decoder into our architecture, leveraging the discrepancy between the outputs given by the two decoders to improve anomaly detection.