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

06/21/2023
by   Nicolae-Catalin Ristea, et al.
0

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 avoiding learning to reconstruct the static background scene. 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. Third, we generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames (without anomalies) and the corresponding pixel-level anomaly maps. Our design leads to an efficient and effective model, as demonstrated by the extensive experiments carried out on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. The empirical results show that our model achieves an excellent trade-off between speed and accuracy, obtaining competitive AUC scores, while processing 1670 FPS. Hence, our model is between 8 and 70 times faster than competing methods. We also conduct an ablation study to justify our design.

READ FULL TEXT

page 1

page 5

page 7

page 8

page 14

page 15

research
11/28/2022

Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation

We propose a very fast frame-level model for anomaly detection in video,...
research
11/19/2019

A Boost Strategy to the Generative Error Based Video Anomaly Detection Algorithms

The generation error (GE) based algorithms show excellent performances i...
research
08/03/2023

Discriminative Graph-level Anomaly Detection via Dual-students-teacher Model

Different from the current node-level anomaly detection task, the goal o...
research
09/04/2023

Prior Knowledge Guided Network for Video Anomaly Detection

Video Anomaly Detection (VAD) involves detecting anomalous events in vid...
research
03/07/2021

Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection

Anomaly detection is a challenging task and usually formulated as an uns...
research
05/03/2018

Detection of Unknown Anomalies in Streaming Videos with Generative Energy-based Boltzmann Models

Abnormal event detection is one of the important objectives in research ...
research
06/22/2023

Triggering Dark Showers with Conditional Dual Auto-Encoders

Auto-encoders (AEs) have the potential to be effective and generic tools...

Please sign up or login with your details

Forgot password? Click here to reset