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

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

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