DISYRE: Diffusion-Inspired Synthetic Restoration for Unsupervised Anomaly Detection

Marimont SN, Baugh M, Siomos V, Tzelepis C, Kainz B, Tarroni G (2024)

Publication Type: Conference contribution

Publication year: 2024

Journal

Proceedings - International Symposium on Biomedical Imaging

Publisher: IEEE Computer Society

Conference Proceedings Title: Proceedings - International Symposium on Biomedical Imaging

Event location: Athens, GRC

ISBN: 9798350313338

DOI: 10.1109/ISBI56570.2024.10635161

Abstract

Unsupervised Anomaly Detection (UAD) techniques aim to identify and localize anomalies without relying on annotations, only leveraging a model trained on a dataset known to be free of anomalies. Diffusion models learn to modify inputs x to increase the probability of it belonging to a desired distribution, i.e., they model the score function ∇x log p(x). Such a score function is potentially relevant for UAD, since ∇x log p(x) is itself a pixel-wise anomaly score. However, diffusion models are trained to invert a corruption process based on Gaussian noise and the learned score function is unlikely to generalize to medical anomalies. This work addresses the problem of how to learn a score function relevant for UAD and proposes DISYRE: Diffusion-Inspired SYnthetic REstoration. We retain the diffusion-like pipeline but replace the Gaussian noise corruption with a gradual, synthetic anomaly corruption so the learned score function generalizes to medical, naturally occurring anomalies. We evaluate DISYRE on three common Brain MRI UAD benchmarks and substantially outperform other methods in two out of the three tasks.

Authors with CRIS profile

Matthew Moses George Baugh
Bernhard Kainz

Involved external institutions

University of London GB United Kingdom (GB) Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB)

How to cite

APA:

Marimont, S.N., Baugh, M., Siomos, V., Tzelepis, C., Kainz, B., & Tarroni, G. (2024). DISYRE: Diffusion-Inspired Synthetic Restoration for Unsupervised Anomaly Detection. In Proceedings - International Symposium on Biomedical Imaging. Athens, GRC: IEEE Computer Society.

MLA:

Marimont, Sergio Naval, et al. "DISYRE: Diffusion-Inspired Synthetic Restoration for Unsupervised Anomaly Detection." Proceedings of the 21st IEEE International Symposium on Biomedical Imaging, ISBI 2024, Athens, GRC IEEE Computer Society, 2024.

BibTeX: Download