City Research Online

Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection

Naval Marimont, S. ORCID: 0000-0002-7075-5586, Siomos, V., Baugh, M. , Tzelepis, C., Kainz, B. & Tarroni, G. ORCID: 0000-0002-0341-6138 (2024). Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection. Paper presented at the MICCAI 2024 27th International Conference, 6-10 Oct 2024, Marrakesh, Morocco. doi: 10.1007/978-3-031-72120-5_23

Abstract

Unsupervised Anomaly Detection (UAD) methods aim to identify anomalies in test samples comparing them with a normative distribution learned from a dataset known to be anomaly-free. Approaches based on generative models offer interpretability by generating anomaly-free versions of test images, but are typically unable to identify subtle anomalies. Alternatively, approaches using feature modelling or self-supervised methods, such as the ones relying on synthetically generated anomalies, do not provide out-of-the-box interpretability. In this work, we present a novel method that combines the strengths of both strategies: a generative cold-diffusion pipeline (i.e., a diffusion-like pipeline which uses corruptions not based on noise) that is trained with the objective of turning synthetically-corrupted images back to their normal, original appearance. To support our pipeline we introduce a novel synthetic anomaly generation procedure, called DAG, and a novel anomaly score which ensembles restorations conditioned with different degrees of abnormality. Our method surpasses the prior state-of-the art for unsupervised anomaly detection in three different Brain MRI datasets.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: This version of the contribution has been accepted for publication, after peer review but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is to be available online at: https://link.springer.com/book/10.1007/978-3-031-72120-5. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms
Publisher Keywords: Unsupervised anomaly detection, diffusion, synthetic
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RC Internal medicine
Departments: School of Science & Technology
School of Science & Technology > Computer Science
SWORD Depositor:
[thumbnail of 2407.06635v1.pdf] Text - Accepted Version
This document is not freely accessible until 3 October 2025 due to copyright restrictions.

To request a copy, please use the button below.

Request a copy

Export

Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login