Unsupervised Anomaly Detection
67 papers with code • 9 benchmarks • 12 datasets
The objective of Unsupervised Anomaly Detection is to detect previously unseen rare objects or events without any prior knowledge about these. The only information available is that the percentage of anomalies in the dataset is small, usually less than 1%. Since anomalies are rare and unknown to the user at training time, anomaly detection in most cases boils down to the problem of modelling the normal data distribution and defining a measurement in this space in order to classify samples as anomalous or normal. In high-dimensional data such as images, distances in the original space quickly lose descriptive power (curse of dimensionality) and a mapping to some more suitable space is required.
However, detecting anomalies in time series data is particularly challenging due to the vague definition of anomalies and said data's frequent lack of labels and highly complex temporal correlations.
To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e. g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation.
Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
At the test stage, the learned memory will be fixed, and the reconstruction is obtained from a few selected memory records of the normal data.
Obtaining models that capture imaging markers relevant for disease progression and treatment monitoring is challenging.
We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images in a one-class learning setting.
Ranked #6 on Anomaly Detection on MVTec AD (using extra training data)
We reused the available code to build scripts for the Reconstruction task and variants with and without memory.
Based on this, we propose a new detection score that is specific to the proposed training scheme.
Ranked #1 on Anomaly Detection on Unlabeled CIFAR-10 vs CIFAR-100
To the best of our knowledge, this is the first comprehensive, multi-object, multi-defect dataset for anomaly detection that provides pixel-accurate ground truth regions and focuses on real-world applications.
Ranked #25 on Anomaly Detection on MVTec AD (Segmentation AUROC metric)