Anomaly Detection

The CIFAR-100 dataset (Canadian Institute for Advanced Research, 100 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The 100 classes in the CIFAR-100 are grouped into 20 superclasses. There are 600 images per class. Each image comes with a "fine" label (the class to which it belongs) and a "coarse" label (the superclass to which it belongs). There are 500 training images and 100 testing images per class. The criteria for deciding whether an image belongs to a class were as follows: * The class name should be high on the list of likely answers to the question “What is in this picture?” * The image should be photo-realistic. Labelers were instructed to reject line drawings. * The image should contain only one prominent instance of the object to which the class refers. * The object may be partially occluded or seen from an unusual viewpoint as long as its identity is still clear to the labeler. Source: https://www.cs.toronto.edu/~kriz/cifar.html Image Source: https://www.cs.toronto.edu/~kriz/cifar.html

The MNIST database (Modified National Institute of Standards and Technology database) is a large collection of handwritten digits. It has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger NIST Special Database 3 (digits written by employees of the United States Census Bureau) and Special Database 1 (digits written by high school students) which contain monochrome images of handwritten digits. The digits have been size-normalized and centered in a fixed-size image. The original black and white (bilevel) images from NIST were size normalized to fit in a 20x20 pixel box while preserving their aspect ratio. The resulting images contain grey levels as a result of the anti-aliasing technique used by the normalization algorithm. the images were centered in a 28x28 image by computing the center of mass of the pixels, and translating the image so as to position this point at the center of the 28x28 field. Source: http://yann.lecun.com/exdb/mnist/ Image Source: https://en.wikipedia.org/wiki/MNIST_database#/media/File:MnistExamples.png

Street View House Numbers (SVHN) is a digit classification benchmark dataset that contains 600,000 32×32 RGB images of printed digits (from 0 to 9) cropped from pictures of house number plates. The cropped images are centered in the digit of interest, but nearby digits and other distractors are kept in the image. SVHN has three sets: training, testing sets and an extra set with 530,000 images that are less difficult and can be used for helping with the training process. Source: Reading Digits in Natural Images with Unsupervised Feature Learning Image Source: http://ufldl.stanford.edu/housenumbers/

Fashion-MNIST is a dataset comprising of 28×28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST shares the same image size, data format and the structure of training and testing splits with the original MNIST. Source: Generative Probabilistic Novelty Detection with Adversarial Autoencoders Image Source: https://github.com/zalandoresearch/fashion-mnist

The STL-10 is an image dataset derived from ImageNet and popularly used to evaluate algorithms of unsupervised feature learning or self-taught learning. Besides 100,000 unlabeled images, it contains 13,000 labeled images from 10 object classes (such as birds, cats, trucks), among which 5,000 images are partitioned for training while the remaining 8,000 images for testing. All the images are color images with 96×96 pixels in size. Source: Unsupervised Feature Learning with C-SVDDNet Image Source: https://cs.stanford.edu/~acoates/stl10/

AG News (AG’s News Corpus) is a subdataset of AG's corpus of news articles constructed by assembling titles and description fields of articles from the 4 largest classes (“World”, “Sports”, “Business”, “Sci/Tech”) of AG’s Corpus. The AG News contains 30,000 training and 1,900 test samples per class. Source: https://arxiv.org/pdf/1509.01626.pdf

The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories. For each object category, there are about 40 to 800 images, while most classes have about 50 images. The resolution of the image is roughly about 300×200 pixels. Source: Simple and Efficient Learning using Privileged Information

MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection. It contains over 5000 high-resolution images divided into fifteen different object and texture categories. Each category comprises a set of defect-free training images and a test set of images with various kinds of defects as well as images without defects. There are two common metrics: Detection AUROC and Segmentation (or pixelwise) AUROC Detection (or, classification) methods output single float (anomaly score) per input test image. Segmentation methods output anomaly probability for each pixel. "To assess segmentation performance, we evaluate the relative per-region overlap of the segmentation with the ground truth. To get an additional performance measure that is independent of the determined threshold, we compute the area under the receiver operating characteristic curve (ROC AUC). We define the true positive rate as the percentage of pixels that were correctly classified as anomalous" [1] Later segmentation metric was improved to balance regions with small and large area, see PRO-AUC and other in [2] Source: MVTEC ANOMALY DETECTION DATASET Image Source: https://www.mvtec.com/company/research/datasets/mvtec-ad/ [1] Paul Bergmann et al, "MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection" [2] Bergmann, P., Batzner, K., Fauser, M. et al. The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. Int J Comput Vis (2021). https://doi.org/10.1007/s11263-020-01400-4

The 20BN-SOMETHING-SOMETHING V2 dataset is a large collection of labeled video clips that show humans performing pre-defined basic actions with everyday objects. The dataset was created by a large number of crowd workers. It allows machine learning models to develop fine-grained understanding of basic actions that occur in the physical world. It contains 220,847 videos, with 168,913 in the training set, 24,777 in the validation set and 27,157 in the test set. There are 174 labels. Source Image Source

The Shanghaitech dataset is a large-scale crowd counting dataset. It consists of 1198 annotated crowd images. The dataset is divided into two parts, Part-A containing 482 images and Part-B containing 716 images. Part-A is split into train and test subsets consisting of 300 and 182 images, respectively. Part-B is split into train and test subsets consisting of 400 and 316 images. Each person in a crowd image is annotated with one point close to the center of the head. In total, the dataset consists of 330,165 annotated people. Images from Part-A were collected from the Internet, while images from Part-B were collected on the busy streets of Shanghai. Source: Iterative Crowd Counting Image Source: Li et al

The ShanghaiTech Campus dataset has 13 scenes with complex light conditions and camera angles. It contains 130 abnormal events and over 270, 000 training frames. Moreover, both the frame-level and pixel-level ground truth of abnormal events are annotated in this dataset.

The UCF-Crime dataset is a large-scale dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies including Abuse, Arrest, Arson, Assault, Road Accident, Burglary, Explosion, Fighting, Robbery, Shooting, Stealing, Shoplifting, and Vandalism. These anomalies are selected because they have a significant impact on public safety. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Source: Video Anomaly Dection Dataset

This dataset contains expert-labeled telemetry anomaly data from the Mars Science Laboratory (MSL) rover, Curiosity. Real spacecraft and curiosity rover anomalies for anomaly detection Indications of telemetry anomalies can be found within previously mentioned ISA reports. All telemetry channels discussed in an individual ISA were reviewed to ensure that the anomaly was evident in the associated telemetry data, and specific anomalous time ranges were manually labeled for each channel. If multiple anomalous sequences and channels closely resembled each other, only one was kept for the experiment in order to create a diverse and balanced set. Anomalies were classified into two categories, point and contextual, to distinguish between anomalies that would likely be identified by properly set alarms or distance-based methods that ignore temporal information (point anomalies) and those that require more complex methodologies such as LSTMs or Hierarchical Temporal Memory (HTM) approaches to detect (contextual anomalies) MSL: TM Channels (27) Total TM values (66,709) Total anomalies (36)

Soil Moisture Active Passive (SMAP) dataset is a dataset of soil samples and telemetry information using the Mars rover by NASA. Originally published in https://arxiv.org/abs/1802.04431 and used for the unsupervised anomaly detection task in time series data. Later it was used in many popular anomaly detection methods and benchmarks that distribute it in their repositories e.g., https://github.com/OpsPAI/MTAD

An open access benchmark dataset comprising of 13,975 CXR images across 13,870 patient cases, with the largest number of publicly available COVID-19 positive cases to the best of the authors' knowledge. Source: COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images

The UCSD Anomaly Detection Dataset was acquired with a stationary camera mounted at an elevation, overlooking pedestrian walkways. The crowd density in the walkways was variable, ranging from sparse to very crowded. In the normal setting, the video contains only pedestrians. Abnormal events are due to either: the circulation of non pedestrian entities in the walkways anomalous pedestrian motion patterns Commonly occurring anomalies include bikers, skaters, small carts, and people walking across a walkway or in the grass that surrounds it. A few instances of people in wheelchair were also recorded. All abnormalities are naturally occurring, i.e. they were not staged for the purposes of assembling the dataset. The data was split into 2 subsets, each corresponding to a different scene. The video footage recorded from each scene was split into various clips of around 200 frames. Source: The UCSD Anomaly Detection Dataset Image Source: http://www.svcl.ucsd.edu/publications/conference/2010/cvpr2010/cvpr_anomaly_2010.pdf

The VisA dataset contains 12 subsets corresponding to 12 different objects as shown in the above figure. There are 10,821 images with 9,621 normal and 1,200 anomalous samples. Four subsets are different types of printed circuit boards (PCB) with relatively complex structures containing transistors, capacitors, chips, etc. For the case of multiple instances in a view, we collect four subsets: Capsules, Candles, Macaroni1 and Macaroni2. Instances in Capsules and Macaroni2 largely differ in locations and poses. Moreover, we collect four subsets including Cashew, Chewing gum, Fryum and Pipe fryum, where objects are roughly aligned. The anomalous images contain various flaws, including surface defects such as scratches, dents, color spots or crack, and structural defects like misplacement or missing parts.

The Yelp Dataset is a valuable resource for academic research, teaching, and learning. It provides a rich collection of real-world data related to businesses, reviews, and user interactions. Here are the key details about the Yelp Dataset: Reviews: A whopping 6,990,280 reviews from users. Businesses: Information on 150,346 businesses. Pictures: A collection of 200,100 pictures. Metropolitan Areas: Data from 11 metropolitan areas. Tips: Over 908,915 tips provided by 1,987,897 users. Business Attributes: Details like hours, parking availability, and ambiance for more than 1.2 million businesses. Aggregated Check-ins: Historical check-in data for each of the 131,930 businesses.

The original ionosphere dataset from UCI machine learning repository is a binary classification dataset with dimensionality 34. There is one attribute having values all zeros, which is discarded. So the total number of dimensions are 33. The ‘bad’ class is considered as outliers class and the ‘good’ class as inliers.

The First Temporal Benchmark Designed to Evaluate Real-time Anomaly Detectors Benchmark The growth of the Internet of Things has created an abundance of streaming data. Finding anomalies in this data can provide valuable insights into opportunities or failures. Yet it’s difficult to achieve, due to the need to process data in real time, continuously learn and make predictions. How do we evaluate and compare various real-time anomaly detection techniques? The Numenta Anomaly Benchmark (NAB) provides a standard, open source framework for evaluating real-time anomaly detection algorithms on streaming data. Through a controlled, repeatable environment of open-source tools, NAB rewards detectors that find anomalies as soon as possible, trigger no false alarms, and automatically adapt to any changing statistics. NAB comprises two main components: a scoring system designed for streaming data and a dataset with labeled, real-world time-series data. Source: Evaluating Real-time Anomaly Detection Algorithms – the Numenta Anomaly Benchmark Image Source: https://numenta.com/machine-intelligence-technology/numenta-anomaly-benchmark/

The Reuters-21578 dataset is a collection of documents with news articles. The original corpus has 10,369 documents and a vocabulary of 29,930 words. Source: Topic Model Based Multi-Label Classification from the Crowd

The BTAD ( beanTech Anomaly Detection) dataset is a real-world industrial anomaly dataset. The dataset contains a total of 2830 real-world images of 3 industrial products showcasing body and surface defects.

XD-Violence is a large-scale audio-visual dataset for violence detection in videos.

Lost and Found is a novel lost-cargo image sequence dataset comprising more than two thousand frames with pixelwise annotations of obstacle and free-space and provide a thorough comparison to several stereo-based baseline methods. The dataset will be made available to the community to foster further research on this important topic. Source: Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles Image Source: http://www.6d-vision.com/lostandfounddataset

This dataset contains images of unusual dangers which can be encountered by a vehicle on the road – animals, rocks, traffic cones and other obstacles. Its purpose is testing autonomous driving perception algorithms in rare but safety-critical circumstances.

Fishyscapes is a public benchmark for uncertainty estimation in a real-world task of semantic segmentation for urban driving. It evaluates pixel-wise uncertainty estimates towards the detection of anomalous objects in front of the vehicle.

Avenue Dataset contains 16 training and 21 testing video clips. The videos are captured in CUHK campus avenue with 30652 (15328 training, 15324 testing) frames in total.

UBnormal is a new supervised open-set benchmark composed of multiple virtual scenes for video anomaly detection. Unlike existing data sets, the data set introduces abnormal events annotated at the pixel level at training time, for the first time enabling the use of fully-supervised learning methods for abnormal event detection. To preserve the typical open-set formulation, the data set includes disjoint sets of anomaly types in the training and test collections of videos.

MVTec 3D Anomaly Detection Dataset (MVTec 3D-AD) is a comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It contains over 4000 high-resolution scans acquired by an industrial 3D sensor. Each of the 10 different object categories comprises a set of defect-free training and validation samples and a test set of samples with various kinds of defects. Precise ground-truth annotations are provided for each anomalous test sample.

MPDD is a dataset aimed at benchmarking visual defect detection methods in industrial metal parts manufacturing. It consists of more than 1000 images with pixel-precise defect annotation masks. The dataset is divided into the training subset with anomaly-free samples and the validation subset that contains both normal and anomalous samples. The dataset can be downloaded at the following link.

A large dataset of musculoskeletal radiographs containing 40,561 images from 14,863 studies, where each study is manually labeled by radiologists as either normal or abnormal. Source: MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs

CASIA-FASD is a small face anti-spoofing dataset containing 50 subjects. Source: Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing Image Source: https://arxiv.org/abs/1511.06316

Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection (MIMII) is a sound dataset of industrial machine sounds. Source: MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection

MVTec Logical Constraints Anomaly Detection (MVTec LOCO AD) dataset is intended for the evaluation of unsupervised anomaly localization algorithms. The dataset includes both structural and logical anomalies. It contains 3644 images from five different categories inspired by real-world industrial inspection scenarios. Structural anomalies appear as scratches, dents, or contaminations in the manufactured products. Logical anomalies violate underlying constraints, e.g., a permissible object being present in an invalid location or a required object not being present at all. The dataset also includes pixel-precise ground truth data for each anomalous region. Source: THE MVTEC LOGICAL CONSTRAINTS ANOMALY DETECTION DATASET (MVTEC LOCO AD)

The MIT-BIH Arrhythmia Database contains 48 half-hour excerpts of two-channel ambulatory ECG recordings, obtained from 47 subjects studied by the BIH Arrhythmia Laboratory between 1975 and 1979. Twenty-three recordings were chosen at random from a set of 4000 24-hour ambulatory ECG recordings collected from a mixed population of inpatients (about 60%) and outpatients (about 40%) at Boston's Beth Israel Hospital; the remaining 25 recordings were selected from the same set to include less common but clinically significant arrhythmias that would not be well-represented in a small random sample. The recordings were digitized at 360 samples per second per channel with 11-bit resolution over a 10 mV range. Two or more cardiologists independently annotated each record; disagreements were resolved to obtain the computer-readable reference annotations for each beat (approximately 110,000 annotations in all) included with the database. This directory contains the entire MIT-BIH Arrhythmia Database. About half (25 of 48 complete records, and reference annotation files for all 48 records) of this database has been freely available here since PhysioNet's inception in September 1999. The 23 remaining signal files, which had been available only on the MIT-BIH Arrhythmia Database CD-ROM, were posted here in February 2005. Much more information about this database may be found in the MIT-BIH Arrhythmia Database Directory.