-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Micorek_2024_CVPR, author = {Micorek, Jakub and Possegger, Horst and Narnhofer, Dominik and Bischof, Horst and Kozinski, Mateusz}, title = {MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18868-18877} }
MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
Abstract
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.
Related Material