Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Croitoru, Florinel-Alin, Ristea, Nicolae-Catalin, Dascalescu, Dana, Ionescu, Radu Tudor, Khan, Fahad Shahbaz, Shah, Mubarak
Format: Preprint
Publié: 2022
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914873494994944
author Croitoru, Florinel-Alin
Ristea, Nicolae-Catalin
Dascalescu, Dana
Ionescu, Radu Tudor
Khan, Fahad Shahbaz
Shah, Mubarak
author_facet Croitoru, Florinel-Alin
Ristea, Nicolae-Catalin
Dascalescu, Dana
Ionescu, Radu Tudor
Khan, Fahad Shahbaz
Shah, Mubarak
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2211_15597
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
Croitoru, Florinel-Alin
Ristea, Nicolae-Catalin
Dascalescu, Dana
Ionescu, Radu Tudor
Khan, Fahad Shahbaz
Shah, Mubarak
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
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.
title Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
url https://arxiv.org/abs/2211.15597