Skip to main content

Research Repository

Advanced Search

AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise

Wyatt, Julian; Leach, Adam; Schmon, Sebastian M.; Willcocks, Chris G.

AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise Thumbnail


Authors

Julian Wyatt

Adam Leach adam.leach@durham.ac.uk
PGR Student Doctor of Philosophy

Sebastian M. Schmon



Abstract

Generative models have been shown to provide a powerful mechanism for anomaly detection by learning to model healthy or normal reference data which can subsequently be used as a baseline for scoring anomalies. In this work we consider denoising diffusion probabilistic models (DDPMs) for unsupervised anomaly detection. DDPMs have superior mode coverage over generative adversarial networks (GANs) and higher sample quality than variational autoencoders (VAEs). However, this comes at the expense of poor scalability and increased sampling times due to the long Markov chain sequences required. We observe that within reconstruction-based anomaly detection a full-length Markov chain diffusion is not required. This leads us to develop a novel partial diffusion anomaly detection strategy that scales to high-resolution imagery, named AnoDDPM. A secondary problem is that Gaussian diffusion fails to capture larger anomalies; therefore we develop a multi-scale simplex noise diffusion process that gives control over the target anomaly size. AnoDDPM with simplex noise is shown to significantly outperform both f-AnoGAN and Gaussian diffusion for the tumorous dataset of 22 T1- weighted MRI scans (CCBS Edinburgh) qualitatively and quantitatively (improvement of +25.5% Sørensen–Dice coefficient, +17.6% IoU and +7.4% AUC).

Citation

Wyatt, J., Leach, A., Schmon, S. M., & Willcocks, C. G. (2022). AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise. . https://doi.org/10.1109/cvprw56347.2022.00080

Presentation Conference Type Conference Paper (Published)
Conference Name 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Start Date Jun 19, 2022
End Date Jun 20, 2022
Acceptance Date May 16, 2022
Online Publication Date Jun 10, 2022
Publication Date 2022-06
Deposit Date Jun 10, 2022
Publicly Available Date Jun 24, 2022
Publisher Institute of Electrical and Electronics Engineers
Pages 649-655
DOI https://doi.org/10.1109/cvprw56347.2022.00080
Public URL https://durham-repository.worktribe.com/output/1136696

Files

Accepted Conference Proceeding (7.7 Mb)
PDF

Copyright Statement
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works






You might also like



Downloadable Citations