Lightning fast video anomaly detection via multi-scale adversarial distillation

Florinel-Alin Croitoru, Nicolae-Catalin Ristea, Dana Dascalescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah

Abstract: Highlights•We introduce a novel teacher-student framework for anomaly detection in video.•We learn to detect anomalies by distilling from multiple highly accurate object-level teachers.•We propose adversarial knowledge distillation in the context of anomaly detection.•To increase the speed, we replace fully connected layers with pointwise convolutions.