Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
arXiv:2211.15597 · doi:10.1016/j.cviu.2024.104074
Abstract
We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. To improve the fidelity of our student, we distill the low-resolution anomaly maps of the teachers by jointly applying standard and adversarial distillation, introducing an adversarial discriminator for each teacher to distinguish between target and generated anomaly maps. We conduct experiments on three benchmarks (Avenue, ShanghaiTech, UCSD Ped2), showing that our method is over 7 times faster than the fastest competing method, and between 28 and 62 times faster than object-centric models, while obtaining comparable results to recent methods. Our evaluation also indicates that our model achieves the best trade-off between speed and accuracy, due to its previously unheard-of speed of 1480 FPS. In addition, we carry out a comprehensive ablation study to justify our architectural design choices. Our code is freely available at: https://github.com/ristea/fast-aed.
Accepted in Computer Vision and Image Understanding
References in corpus (12)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
- Knowledge Distillation: A Survey
- Deep Learning for Anomaly Detection: A Review
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
- Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
- Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events
- A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video
- Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection
- Feature-map-level Online Adversarial Knowledge Distillation
- Anomaly Detection in Aerial Videos with Transformers
- CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation