59 datasets found

Spot-the-difference self-supervised pre-training for anomaly detection and segmentation.

Training a unified model is considered to be more suitable for practical industrial anomaly detection scenarios due to its generalization ability and storage efficiency....

Vibration sensor data from five rotating machines

Vibration sensor data from four bearings

Two real-world datasets for condition monitoring and anomaly detection in rotating machines

The dataset used in this paper for anomaly multimedia traffic identification in graynet.

The KDD Cup 1999 dataset contains a set of instances that represent connections to a military computer network.

The dataset used in this paper is the KDDCUP99 dataset, which contains network traffic data from a military network.

A dataset for evaluating anomaly explanation methods. It contains 22,722 manually labelled frames in ShanghaiTech, Avenue, and UCSD Ped2.

The UCSD dataset is a benchmark for the analysis of abnormal detection and localization in crowded scenes.

A common study area in anomaly identification is industrial images anomaly detection based on texture background.

A common study area in anomaly identification is industrial images anomaly detection based on texture background.

A common study area in anomaly identification is industrial images anomaly detection based on texture background.

A common study area in anomaly identification is industrial images anomaly detection based on texture background.

A custom dataset of four unique types of carpet textures was created to thoroughly test state-of-the-art unsupervised detection models.

A public credit card transaction dataset from Kaggle website, which contains 492 frauds out of 284,807 transactions.

The LANL dataset consists of over one billion log lines collected over 58 consecutive days. The logs contain anonymized process, network flow, DNS, and authentication information.

Video anomaly detection has great potential in enhancing safety in the production and monitoring of crucial areas. Currently, most video anomaly detection methods are based on...

The shuttle dataset is used for anomaly clustering and visualization. It contains 9 numerical attributes and 7 classes.

The dataset is used for multivariate anomaly detection on time series data generated by cyber-physical systems.