Papers with Code 아카이브

Anomaly Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
28
평가표
76
보존된 평가 기록
669

Anomaly Detection is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.

[Image source]: GAN-based Anomaly Detection in Imbalance Problems

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

How do I Contact Expedia Customer Service 24/7 hours

Can I contact Expedia by phone? To speak to someone at Expedia, call their customer service at 1-800-EXPEDIA (1-888-829-0881). For additional support, you can also reach them at 1-888-829-0881. Alternatively, visit the “Help” section on their website for more contact options. To speak to someone on Expedia, you should: Contact Expedia customer service hotline at +1-888-829-0881 or +1-888-829-0881 Provide details of the issue or inconvenience you experienced. Follow any instructions provided by the customer support representative You can request a refund by either using the online platform on Expedia’s website or directly contacting their customer serviceBeginner+1-888-829-0881 Beginner. To initiate a refund, simply cancel your flight ticket and request a refund through the customer service number at Beginner+1-888-829-0881Telephone. or Expedia® “+1-888-829-0881Telephone To provide feedback on your support experience and contribute to improving service quality +1-888-829-0881 , you can speak with a live agent by calling Expedia’s 247 customer service hotline at +1-888-829-0881 .

IDE

This data set allows to systematically evaluate approaches for the task of identifying anomalies and extreme events in water cycle components by developing deep neural networks that detect anomalies and drivers of extremes in simulated data.

Industrial Benchmark Dataset for Customer Escalation Prediction

This is a real-world industrial benchmark dataset from a major medical device manufacturer for the prediction of customer escalations. The dataset contains features derived from IoT (machine log) and enterprise data including labels for escalation from a fleet of thousands of customers of high-end medical devices. The dataset accompanies the publication "System Design for a Data-driven and Explainable Customer Sentiment Monitor" (submitted). We provide an anonymized version of data collected over a period of two years. The dataset should fuel the research and development of new machine learning algorithms to better cope with real-world data challenges including sparse and noisy labels, and concept drifts. Additional challenges are the optimal fusion of enterprise and log-based features for the prediction task. Thereby, the interpretability of designed prediction models should be ensured in order to have practical relevancy. Supporting software Kindly use the corresponding GitHub repository (https://github.com/annguy/customer-sentiment-monitor) to design and benchmark your algorithms. Citation and Contact If you use this dataset please cite the following publication: @ARTICLE{9520354, author={Nguyen, An and Foerstel, Stefan and Kittler, Thomas and Kurzyukov, Andrey and Schwinn, Leo and Zanca, Dario and Hipp, Tobias and Jun, Sun Da and Schrapp, Michael and Rothgang, Eva and Eskofier, Bjoern}, journal={IEEE Access}, title={System Design for a Data-Driven and Explainable Customer Sentiment Monitor Using IoT and Enterprise Data}, year={2021}, volume={9}, number={}, pages={117140-117152}, doi={10.1109/ACCESS.2021.3106791}} If you would like to get in touch, please contact an.nguyen@fau.de.

IoT-23

IoT-23 is a dataset of network traffic from Internet of Things (IoT) devices. It has 20 malware captures executed in IoT devices, and 3 captures for benign IoT devices traffic. It was first published in January 2020, with captures ranging from 2018 to 2019. These IoT network traffic was captured in the Stratosphere Laboratory, AIC group, FEL, CTU University, Czech Republic. Its goal is to offer a large dataset of real and labeled IoT malware infections and IoT benign traffic for researchers to develop machine learning algorithms. This dataset and its research was funded by Avast Software. The malware was allow to connect to the Internet.

ISP-AD

The ISP-AD Dataset is a large-scale anomaly detection dataset, representing a real-world industrial use case. It contains 312,674 fault-free and 246,375 defective samples, including 245,664 synthetic defects and 711 real defects collected on the factory floor. Designed to advance research in unsupervised, self-supervised, and supervised anomaly detection, ISP-AD serves as a benchmark for evaluating defect detection methods under realistic industrial conditions.

ITD

This dataset aims to provide a color dataset with real industrial fabric defect gathered in a visiting machine with several industrial cameras. It has been designed with the same nomenclature as MVTEC AD dataset

ITDD

The Industrial Textile Defect Detection (ITDD) dataset includes 1885 industrial textile images categorized into 4 categories: cotton fabric, dyed fabric, hemp fabric, and plaid fabric. These classes are collected from the industrial production sites of WEIQIAO Textile. ITDD is an upgraded version of WFDD that reorganizes three original classes and adds one new class.

MVTec-AC

MVTec-AC is a curated refinement of the widely-used MVTec-AD dataset, specifically designed for anomaly classification—distinguishing between different types of anomalies rather than merely detecting if an image is anomalous. While MVTec-AD focuses on binary detection and suffers from mislabeled or ambiguous samples, MVTec-AC introduces manually corrected labels and reorganized anomaly categories to enable robust multi-class evaluation. Key improvements include the correction of 36 misclassified samples, merging of 4 overlapping classes, removal of 4 ambiguous ‘combined’ classes, and exclusion of the toothbrush category, which contains only a single trivial anomaly type. These changes support consistent, fine-grained assessment of classification models in industrial visual inspection contexts.

ODDS

Outliers or anomalies are instances that do not conform to the norm of a dataset. Outlier detection is an important data mining problem that has been researched within diverse research areas and applications domains such as intrusion detection, fraud detection, unusual event detection, disease condition detection etc. The exact notion of an outlier is different for different application domains. Hence, applying a technique developed for one domain to another is not straightforward. Moreover, availability of labeled data for training/validation of outlier detection methods is scarce and often noise contained in data tends to be similar to outliers, thus makes it difficult to distinguish them. Because of these challenges outlier detection is not an easy problem to solve. Furthermore, research on outlier detection has been held back by the lack of good benchmark datasets with ground truths. Existing benchmarks are typically either proprietary or else very artificial. Moreover, existing real-world outlier/anomaly detection datasets lack the availability of ground truth. In ODDS, we openly provide access to a large collection of outlier detection datasets with ground truth (if available). Our focus is to provide datasets from different domains and present them under a single platform for the research community. As such, we arrange the datasets based on their types into different tables in ODDS library. The ODDS library is being actively developed since summer 2016 and is growing as a result of our research pursuits in outlier/anomaly mining and also to help the corresponding research community. Researchers are welcome to share their datasets with us to include in ODDS library by emailing srayana@cs.stonybrook.edu.

PRONTO

The PRONTO heterogeneous benchmark dataset is based on an industrial-scale multiphase flow facility. It includes data from heterogeneous sources, including process measurements, alarm records, high frequency ultrasonic flow and pressure measurements, an operation log and video recordings. The study collected data from various operational conditions with and without induced faults to generate a multi-rate, multi-modal dataset. The dataset is suitable for developing and validating algorithms for fault detection and diagnosis (FDD) and data fusion.

Radio observatory anomaly detection dataset

The ROAD dataset is made up of observations from the Low Frequency Array (LOFAR) telescope. LOFAR is comprised of 52 stations across Europe, where each station is an array of 96 dual polarisation low-band antennas (LBA) in the 10–90 MHz range and 48 or 96 dual polarisation high-band antenna antennas (HBA) in the 110–250 MHz range. The data are four dimensional, with the dimensions corresponding to time, frequency, polarisation, and station. dictate the array configuration (i.e. the number of stations used), the number of frequency channels (Nf), the time sampling, as well as the overall integration time (Nt) of the observing session. Furthermore, the dual-polarisation of the antennas results in a correlation product (Npol) of size 4. The ROAD dataset contains ten classes that describe various system-wide phenomena and anomalies from data obtained by the LOFAR telescope. These classes are categorised into four groups: data processing system failures, electronic anomalies, environmental effects, and unwanted astronomical events as shown by the table below. | Category | Description | Band | Polarisation | Occurrence rate | ** Num Samples** | |--------------------------------|-------------------------------------------------------------|-------------------|---------------------------|------------------------------|--------------------------| | Normal | All non-characterised effects | Both | All | - | 4687 | | % Electric fence | RFI emitted from electric fences | Low | Cross | 64 | | Data processing | | | | | | | First order data loss | Data loss from consecutive time and/or frequency channels | Both | All | 0.02 | 146 | | Second order data loss | Data loss from single frequency and/or single time channels | Both | All | 0.04 | 283 | | Electronic systems | | | | | | | High noise element | High power disturbances caused by miscellaneous events | Both | All | 0.01 | 88 | | Oscillating tile | Amplifier going into oscillation | High | All | 0.01 | 56 | | Astronomical events | | | | | | | Source in side-lobes | A-team source passing through side-lobes | High | All | 0.06 | 446 | | Galactic plane | Galactic plane passing through the main lobe of the antenna | Both | Cross | 0.08 | 550 | | Solar storm | Strong emissions from the sun | Low | All | 0.02 | 147 | | Environmental effects | | | | | | | Lightning | Lightning storm | Both | All | 0.06 | 389 | | Ionospheric RFI reflections | RFI reflected from the ionosphere | Low | All | 0.04 | 261 |

Riseholme-2021

Risholme-2021 contains >3.5K images of strawberries at various growth stages along with anomalous instances. Data collection was performed in the strawberry research farm at the Riseholme campus of the University of Lincoln in UK. For more details, please check out "Homepage" down below.

Simulated micro-Doppler Signatures

Simulated pulse Doppler radar signatures for four classes of helicopter-like targets. The classes differ in the number of rotating blades each kind of target carries, thus each class translates into a specific modulation pattern on the Doppler signature. Doppler signatures are a typical feature used to achieve radar targets discrimination. This dataset was generated using a simple open-source MATLAB simulation code, which can be easily modified to generate custom datasets with more classes and increased intra-class diversity. Dataset can be easily used for supervised classification, out-of-distribution detection (near and far), unsupervised learning and modulation pattern segmentation. The code includes the generation of an SPD representation for each signature, thanks to the computation of a covariance matrix, thus allowing for second-order specific data processing (e.g. Riemannian neural network or tangent PCA). Dataset used in the paper Dataset generation code

SPOT-10

The SPOTS-10 dataset is an extensive collection of grayscale images showcasing diverse patterns found in ten animal species. Specifically, SPOTS-10 contains 50,000 32 x 32 grayscale images, divided into ten categories, with 5,000 images per category. The training set comprises 40,000 images, while the test set contains 10,000 images. The SPOTS-10 dataset is freely available on the project GitHub page: https://github.com/amotica/spots-10 by cloning the repository.

VADD

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

VFD-2000

VFD-2000 is a video fight detection dataset containing more than 2000 videos. YouTube is the data source. Specific scenarios are searched using “fight” as a search keyword, for example, “street fight”, “beach fight”, and “violence in the restaurant”. 200 videos under 20 different scenes are collected.

VisA-AC

VisA-AC is a refined benchmark based on the VisA dataset, tailored for the task of anomaly classification—distinguishing between different types of anomalies rather than simply detecting whether an image is anomalous. While the original VisA provides anomaly type information in an Excel file, it includes numerous under-sampled and ambiguous classes. VisA-AC addresses these issues by removing classes with fewer than 10 samples, merging visually similar categories, and manually correcting mislabeled samples. Additionally, anomaly classes in VisA-AC are organized into separate folders—following the structure of MVTec-AC—for easier integration and usage. The resulting dataset ensures both statistical robustness and semantic clarity, supporting rigorous evaluation of multi-class anomaly classification methods in real-world industrial settings.

ADFI

ADFI Dataset is an image dataset for anomaly detection methods with a focus on industrial inspection. Each category sub dataset comprises a training set of images and a test set of images with various kinds of defects as well as images without defects. Supplementary information: ADFI provides a cloud service that automatically creates machine learning models for anomaly detection. You can create anomaly detection models with these datasets for free on the ADFI website.

CamNuvem Dataset

This dataset focuses only on the robbery category, presenting a new weakly labelled dataset that contains 486 new real–world robbery surveillance videos acquired from public sources.

Digital Forensics 2023 dataset - DF2023

The deliberate manipulation of public opinion, especially through altered images, poses a significant danger to society. To fight this issue on a technical level we support the research community by releasing the Digital Forensics 2023 (DF2023) training and validation dataset. The DF2023 training dataset comprises one million images from four major forgery categories: * splicing (400K) * copy-move (300K) * enhancement (200K) * removal (100K) This dataset enables an objective comparison of network architectures and can significantly reduce the time and effort of researchers preparing datasets. For a detailed description of the DF2023 dataset, please refer to: @inproceedings{Fischinger2023DFNet, title={DF2023: The Digital Forensics 2023 Dataset for Image Forgery Detection}, author={David Fischinger and Martin Boyer}, journal={The 25th Irish Machine Vision and Image Processing conference. (IMVIP)}, year={2023} } available from: Zenodo ## Naming convention The naming convention of DF2023 encodes information about the applied manipulations. Each image name has the following form: COCO_DF_0123456789_NNNNNNNN.{EXT} (e.g. COCO_DF_E000G40117_00200620.jpg) After the identifier of the image data source ("COCO") and the self-reference to the Digital Forensics ("DF") dataset, there are 10 digits as placeholders for the manipulation. Position 0 defines the manipulation types copy-move, splicing, removal, enhancement ([C,S,R,E]). The following digits 1-9 represent donor patch manipulations. For positions [1,2,7,8] (resample, flip, noise and brightness), a binary value indicates if this manipulation was applied to the donor image patch. Position 3 (rotate) indicates by the values 0-3 if the rotation was executed by 0, 90, 180 or 270 degrees. Position 4 defines if BoxBlur (B) or GaussianBlur (G) was used. Position 5 specifies the blurring radius. A value of 0 indicates that no blurring was executed. Position 6 indicates which of the Python-PIL contrast filters EDGE ENHANCE, EDGE ENHANCE MORE, SHARPEN, UnsharpMask or ImageEnhance (values 1-5) was applied. If none of them was applied, this value is set to 0. Finally, position 9 is set to the JPEG compression factor modulo 10, a value of 0 indicates that no JPEG compression was applied. The 8 characters NNNNNNNN in the image name template stand for a running number of the images.

DIS100k

This is an image splicing dataset including different types of preprocessing and postprocessing techniques. Foreground objects are taken from HRSOD and background images are taken from BG20k datasets. 95000 train and 5000 test images are provided.

Lusitano Fabric Defect Detection Dataset

The Lusitano dataset was collected over a 3-month period, spanning from January to March, from Paulo de Oliveira, S.A., a prominent textile company, based in Covilhã, Portugal, renowned for its innovative contributions to the textile industry. To collect the images for the dataset, we placed one camera in front of a fabric inspection machine, along with a strong and nearly uniform light source. This dataset comprises 4096 × 1024 images, captured by an industrial-grade Teledyne Dalsa Linea camera. The camera’s high resolution and precision ensure the accurate depiction of textile samples, with the level of detail necessary for defect analysis. None of the defects depicted in this dataset are artificially generated; they stem from genuine occurrences observed during this collection period, and thus represent real-world challenges encountered in textile production processes. The dataset also showcases normal images. We announce two folders, train and test in the same folder architecture, a MVTEC AD dataset. The training set contains 32k normal images, while the testing set contains 1646 defect images and 1038 normal images

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.