Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
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.
Code (1)
Tasks
Anomaly DetectionKnowledge DistillationVideo Anomaly DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AnimateDiff-Lightning: Cross-Model Diffusion Distillation
We present AnimateDiff-Lightning for lightning-fast video generation. Our model uses progressive adversarial diffusion distillation to achieve new state-of-the-art in few-step video generation. We discuss our modificatio…
modelVideo GenerationAdversarial Machine Learning Attacks Against Video Anomaly Detection Systems
Anomaly detection in videos is an important computer vision problem with various applications including automated video surveillance. Although adversarial attacks on image understanding models have been heavily investiga…
Anomaly DetectionBIG-bench Machine LearningVideo Anomaly DetectionVideo UnderstandingReward Lightning: Fast Video Generation via Homologous Preference Distillation
Achieving simultaneous preference alignment and distillation acceleration in video diffusion models remains an open challenge. Existing methods optimize the two objectives over mismatched representation spaces, where imp…
Video GenerationLightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos
Accuracy and speed are critical in image editing tasks. Pan et al. introduced a drag-based image editing framework that achieves pixel-level control using Generative Adversarial Networks (GANs). A flurry of subsequent st…
Predicting Next Local Appearance for Video Anomaly Detection
We present a local anomaly detection method in videos. As opposed to most existing methods that are computationally expensive and are not very generalizable across different video scenes, we propose an adversarial framew…
Anomaly DetectionObjectVideo Anomaly Detection