A unifying review of deep and shallow anomaly detection

L Ruff, JR Kauffmann, RA Vandermeulen… - Proceedings of the …, 2021 - ieeexplore.ieee.org
Deep learning approaches to anomaly detection (AD) have recently improved the state of
the art in detection performance on complex data sets, such as large collections of images or …

Mood 2020: A public benchmark for out-of-distribution detection and localization on medical images

D Zimmerer, PM Full, F Isensee, P Jäger… - … on Medical Imaging, 2022 - ieeexplore.ieee.org
Detecting Out-of-Distribution (OoD) data is one of the greatest challenges in safe and robust
deployment of machine learning algorithms in medicine. When the algorithms encounter …

Detecting outliers with poisson image interpolation

J Tan, B Hou, T Day, J Simpson, D Rueckert… - … Image Computing and …, 2021 - Springer
Supervised learning of every possible pathology is unrealistic for many primary care
applications like health screening. Image anomaly detection methods that learn normal …

Anomaly detection through latent space restoration using vector quantized variational autoencoders

SN Marimont, G Tarroni - 2021 IEEE 18th International …, 2021 - ieeexplore.ieee.org
We propose an out-of-distribution detection method that combines density and restoration-
based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ …

Implicit field learning for unsupervised anomaly detection in medical images

S Naval Marimont, G Tarroni - … , France, September 27–October 1, 2021 …, 2021 - Springer
We propose a novel unsupervised out-of-distribution detection method for medical images
based on implicit fields image representations. In our approach, an auto-decoder feed …

Unsupervised anomaly localization with structural feature-autoencoders

F Meissen, J Paetzold, G Kaissis… - International MICCAI …, 2022 - Springer
Abstract Unsupervised Anomaly Detection has become a popular method to detect
pathologies in medical images as it does not require supervision or labels for training. Most …

On the pitfalls of using the residual as anomaly score

F Meissen, B Wiestler, G Kaissis… - Medical Imaging with …, 2022 - openreview.net
Many current state-of-the-art methods for anomaly detection in medical images rely on
calculating a residual image between a potentially anomalous input image and its (" …

Trustworthy in silico cell labeling via ensemble-based image translation

S Imboden, X Liu, MC Payne, CJ Hsieh, NYC Lin - Biophysical Reports, 2023 - cell.com
Artificial intelligence (AI) image translation has been a valuable tool for processing image
data in biological and medical research. To apply such a tool in mission-critical applications …

Cradl: Contrastive representations for unsupervised anomaly detection and localization

CT Lüth, D Zimmerer, G Koehler, PF Jaeger… - arXiv preprint arXiv …, 2023 - arxiv.org
Unsupervised anomaly detection in medical imaging aims to detect and localize arbitrary
anomalies without requiring annotated anomalous data during training. Often, this is …

Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction

T Peng, Y Zheng, L Zhao, E Zheng - Sensors, 2024 - mdpi.com
The occurrence of anomalies on the surface of industrial products can lead to issues such as
decreased product quality, reduced production efficiency, and safety hazards. Early …