Confidence-Aware and Self-supervised Image Anomaly Localisation

Müller J, Baugh M, Tan J, Dombrowski M, Kainz B (2023)

Publication Type: Conference contribution

Publication year: 2023

Journal

Lecture Notes in Computer Science Springer Verlag

Publisher: IEEE

Series: Lecture Notes in Computer Science

Book Volume: 14291

Pages Range: 177-187

Conference Proceedings Title: Uncertainty for Safe Utilization of Machine Learning in Medical Imaging

Event location: Vancouver CA

ISBN: 9783031443350

DOI: 10.1007/978-3-031-44336-7_18

Abstract

Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty estimates, auto-encoding models, or from synthetic anomalies in a self-supervised way. The performance of self-supervised anomaly detection approaches is still inferior compared to methods that use examples from known unknown classes to shape the decision boundary. However, outlier exposure methods often do not identify unknown unknowns. Here we discuss an improved self-supervised single-class training strategy that supports the approximation of probabilistic inference with loosen feature locality constraints. We show that up-scaling of gradients with histogram-equalised images is beneficial for recently proposed self-supervision tasks. Our method is integrated into several out-of-distribution (OOD) detection models and we show evidence that our method outperforms the state-of-the-art on various benchmark datasets.

Authors with CRIS profile

Johanna Müller Professur für Image Data Exploration and Analysis Matthew Moses George Baugh
Mischa Dombrowski Professur für Image Data Exploration and Analysis Bernhard Kainz Professur für Image Data Exploration and Analysis

Involved external institutions

Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich CH Switzerland (CH) Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB)

How to cite

APA:

Müller, J., Baugh, M., Tan, J., Dombrowski, M., & Kainz, B. (2023). Confidence-Aware and Self-supervised Image Anomaly Localisation. In Carole H. Sudre, Christian F. Baumgartner, Adrian Dalca, Raghav Mehta, Chen Qin, William M. Wells (Eds.), Uncertainty for Safe Utilization of Machine Learning in Medical Imaging (pp. 177-187). Vancouver, CA: IEEE.

MLA:

Müller, Johanna, et al. "Confidence-Aware and Self-supervised Image Anomaly Localisation." Proceedings of the Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, Vancouver Ed. Carole H. Sudre, Christian F. Baumgartner, Adrian Dalca, Raghav Mehta, Chen Qin, William M. Wells, IEEE, 2023. 177-187.

BibTeX: Download