MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Micorek, Jakub, Possegger, Horst, Narnhofer, Dominik, Bischof, Horst, Kozinski, Mateusz
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917619089539072
author Micorek, Jakub
Possegger, Horst
Narnhofer, Dominik
Bischof, Horst
Kozinski, Mateusz
author_facet Micorek, Jakub
Possegger, Horst
Narnhofer, Dominik
Bischof, Horst
Kozinski, Mateusz
contents We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network. This lets us estimate the likelihood of test videos and detect video anomalies by thresholding the likelihood estimates. We train our video anomaly detector using a modification of denoising score matching, a method that injects training data with noise to facilitate modeling its distribution. To eliminate hyperparameter selection, we model the distribution of noisy video features across a range of noise levels and introduce a regularizer that tends to align the models for different levels of noise. At test time, we combine anomaly indications at multiple noise scales with a Gaussian mixture model. Running our video anomaly detector induces minimal delays as inference requires merely extracting the features and forward-propagating them through a shallow neural network and a Gaussian mixture model. Our experiments on five popular video anomaly detection benchmarks demonstrate state-of-the-art performance, both in the object-centric and in the frame-centric setup.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14497
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
Micorek, Jakub
Possegger, Horst
Narnhofer, Dominik
Bischof, Horst
Kozinski, Mateusz
Computer Vision and Pattern Recognition
We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network. This lets us estimate the likelihood of test videos and detect video anomalies by thresholding the likelihood estimates. We train our video anomaly detector using a modification of denoising score matching, a method that injects training data with noise to facilitate modeling its distribution. To eliminate hyperparameter selection, we model the distribution of noisy video features across a range of noise levels and introduce a regularizer that tends to align the models for different levels of noise. At test time, we combine anomaly indications at multiple noise scales with a Gaussian mixture model. Running our video anomaly detector induces minimal delays as inference requires merely extracting the features and forward-propagating them through a shallow neural network and a Gaussian mixture model. Our experiments on five popular video anomaly detection benchmarks demonstrate state-of-the-art performance, both in the object-centric and in the frame-centric setup.
title MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.14497